{ "languages": [ { "bcp_47": "en", "speakers": 1636485840, "language_name": "English", "autonym": "English", "family": "Indo-European", "flores_path": "eng_Latn", "fleurs_tag": "en_us", "commonvoice_hours": 2660.0, "commonvoice_locale": "en", "in_benchmark": true }, { "bcp_47": "zh", "speakers": 1304678914, "language_name": "Chinese", "autonym": "中文", "family": "Sino-Tibetan", "flores_path": "cmn_Hans", "fleurs_tag": "cmn_hans_cn", "commonvoice_hours": 422.0, "commonvoice_locale": "zh-TW", "in_benchmark": true }, { "bcp_47": "hi", "speakers": 546882144, "language_name": "Hindi", "autonym": "हिन्दी", "family": "Indo-European", "flores_path": "hin_Deva", "fleurs_tag": "hi_in", "commonvoice_hours": 16.0, "commonvoice_locale": "hi-IN", "in_benchmark": true }, { "bcp_47": "es", "speakers": 493528077, "language_name": "Spanish", "autonym": "Español", "family": "Indo-European", "flores_path": "spa_Latn", "fleurs_tag": "es_419", "commonvoice_hours": 447.0, "commonvoice_locale": "es", "in_benchmark": true }, { "bcp_47": "ar", "speakers": 351664197, "language_name": "Arabic", "autonym": "العربية", "family": "Afro-Asiatic", "flores_path": "arb_Arab", "fleurs_tag": "ar_eg", "commonvoice_hours": 92.0, "commonvoice_locale": "ar", "in_benchmark": true }, { "bcp_47": "ur", "speakers": 290790290, "language_name": "Urdu", "autonym": "اردو", "family": "Indo-European", "flores_path": "urd_Arab", "fleurs_tag": "ur_pk", "commonvoice_hours": 77.0, "commonvoice_locale": "ur", "in_benchmark": true }, { "bcp_47": "fr", "speakers": 278611507, "language_name": "French", "autonym": "Français", "family": "Indo-European", "flores_path": "fra_Latn", "fleurs_tag": "fr_fr", "commonvoice_hours": 1056.0, "commonvoice_locale": "fr", "in_benchmark": true }, { "bcp_47": "bn", "speakers": 267193288, "language_name": "Bangla", "autonym": "বাংলা", "family": "Indo-European", "flores_path": "ben_Beng", "fleurs_tag": "bn_in", "commonvoice_hours": 49.0, "commonvoice_locale": "bn", "in_benchmark": true }, { "bcp_47": "pt", "speakers": 237496885, "language_name": "Portuguese", "autonym": "Português", "family": "Indo-European", "flores_path": "por_Latn", "fleurs_tag": "pt_br", "commonvoice_hours": 178.0, "commonvoice_locale": "pt", "in_benchmark": true }, { "bcp_47": "pa", "speakers": 203571210, "language_name": "Punjabi", "autonym": "ਪੰਜਾਬੀ", "family": "Indo-European", "flores_path": "pan_Guru", "fleurs_tag": "pa_in", "commonvoice_hours": 2.3, "commonvoice_locale": "pa-IN", "in_benchmark": true }, { "bcp_47": "ru", "speakers": 195841151, "language_name": "Russian", "autonym": "Русский", "family": "Indo-European", "flores_path": "rus_Cyrl", "fleurs_tag": "ru_ru", "commonvoice_hours": 244.0, "commonvoice_locale": "ru", "in_benchmark": true }, { "bcp_47": "sw", "speakers": 171610296, "language_name": "Swahili", "autonym": "Kiswahili", "family": "Atlantic-Congo", "flores_path": "swh_Latn", "fleurs_tag": "sw_ke", "commonvoice_hours": 411.0, "commonvoice_locale": "sw", "in_benchmark": true }, { "bcp_47": "id", "speakers": 171207687, "language_name": "Indonesian", "autonym": "Bahasa Indonesia", "family": "Austronesian", "flores_path": "ind_Latn", "fleurs_tag": "id_id", "commonvoice_hours": 33.0, "commonvoice_locale": "id", "in_benchmark": true }, { "bcp_47": "de", "speakers": 136350226, "language_name": "German", "autonym": "Deutsch", "family": "Indo-European", "flores_path": "deu_Latn", "fleurs_tag": "de_de", "commonvoice_hours": 1362.0, "commonvoice_locale": "de", "in_benchmark": true }, { "bcp_47": "ja", "speakers": 119729026, "language_name": "Japanese", "autonym": "日本語", "family": "Japonic", "flores_path": "jpn_Jpan", "fleurs_tag": "ja_jp", "commonvoice_hours": 223.0, "commonvoice_locale": "ja", "in_benchmark": true }, { "bcp_47": "te", "speakers": 95478480, "language_name": "Telugu", "autonym": "తెలుగు", "family": "Dravidian", "flores_path": "tel_Telu", "fleurs_tag": "te_in", "commonvoice_hours": 0.3, "commonvoice_locale": "te", "in_benchmark": true }, { "bcp_47": "lah", "speakers": 93433552, "language_name": "Western Panjabi", "autonym": "لہندا پنجابی", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mr", "speakers": 92826300, "language_name": "Marathi", "autonym": "मराठी", "family": "Indo-European", "flores_path": "mar_Deva", "fleurs_tag": "mr_in", "commonvoice_hours": 20.0, "commonvoice_locale": "mr", "in_benchmark": true }, { "bcp_47": "jv", "speakers": 91180665, "language_name": "Javanese", "autonym": "Jawa", "family": "Austronesian", "flores_path": "jav_Latn", "fleurs_tag": "jv_id", "commonvoice_hours": 0.0, "commonvoice_locale": "jv", "in_benchmark": true }, { "bcp_47": "vi", "speakers": 86222962, "language_name": "Vietnamese", "autonym": "Tiếng Việt", "family": "Austroasiatic", "flores_path": "vie_Latn", "fleurs_tag": "vi_vn", "commonvoice_hours": 6.2, "commonvoice_locale": "vi", "in_benchmark": true }, { "bcp_47": "ta", "speakers": 85616159, "language_name": "Tamil", "autonym": "தமிழ்", "family": "Dravidian", "flores_path": "tam_Taml", "fleurs_tag": "ta_in", "commonvoice_hours": 235.0, "commonvoice_locale": "ta", "in_benchmark": true }, { "bcp_47": "fa", "speakers": 84710459, "language_name": "Persian", "autonym": "فارسی", "family": "Indo-European", "flores_path": "pes_Arab", "fleurs_tag": "fa_ir", "commonvoice_hours": 370.0, "commonvoice_locale": "fa", "in_benchmark": true }, { "bcp_47": "wuu", "speakers": 83641200, "language_name": "Wu Chinese", "autonym": "Wu Chinese", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tr", "speakers": 80360704, "language_name": "Turkish", "autonym": "Türkçe", "family": "Turkic", "flores_path": "tur_Latn", "fleurs_tag": "tr_tr", "commonvoice_hours": 128.0, "commonvoice_locale": "tr", "in_benchmark": true }, { "bcp_47": "yue", "speakers": 79654759, "language_name": "Cantonese", "autonym": "粵語", "family": "Sino-Tibetan", "flores_path": "yue_Hant", "fleurs_tag": "yue_hant_hk", "commonvoice_hours": 203.0, "commonvoice_locale": "yue", "in_benchmark": true }, { "bcp_47": "ko", "speakers": 78357046, "language_name": "Korean", "autonym": "한국어", "family": "Koreanic", "flores_path": "kor_Hang", "fleurs_tag": "ko_kr", "commonvoice_hours": 1.7, "commonvoice_locale": "ko", "in_benchmark": true }, { "bcp_47": "it", "speakers": 70247060, "language_name": "Italian", "autonym": "Italiano", "family": "Indo-European", "flores_path": "ita_Latn", "fleurs_tag": "it_it", "commonvoice_hours": 362.0, "commonvoice_locale": "it", "in_benchmark": true }, { "bcp_47": "fil", "speakers": 67471096, "language_name": "Filipino", "autonym": "Filipino", "family": "Austronesian", "flores_path": "fil_Latn", "fleurs_tag": "fil_ph", "commonvoice_hours": 0.0, "commonvoice_locale": "tl", "in_benchmark": true }, { "bcp_47": "arz", "speakers": 66639360, "language_name": "Egyptian Arabic", "autonym": "Egyptian Arabic", "family": "Afro-Asiatic", "flores_path": "arz_Arab", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "gu", "speakers": 61721799, "language_name": "Gujarati", "autonym": "ગુજરાતી", "family": "Indo-European", "flores_path": "guj_Gujr", "fleurs_tag": "gu_in", "commonvoice_hours": 0.0, "commonvoice_locale": "gu-IN", "in_benchmark": true }, { "bcp_47": "th", "speakers": 55181920, "language_name": "Thai", "autonym": "ไทย", "family": "Tai-Kadai", "flores_path": "tha_Thai", "fleurs_tag": "th_th", "commonvoice_hours": 172.0, "commonvoice_locale": "th", "in_benchmark": true }, { "bcp_47": "ps", "speakers": 53542641, "language_name": "Pashto", "autonym": "پښتو", "family": "Indo-European", "flores_path": null, "fleurs_tag": "ps_af", "commonvoice_hours": 81.0, "commonvoice_locale": "ps", "in_benchmark": false }, { "bcp_47": "kn", "speakers": 49065330, "language_name": "Kannada", "autonym": "ಕನ್ನಡ", "family": "Dravidian", "flores_path": "kan_Knda", "fleurs_tag": "kn_in", "commonvoice_hours": 0.0, "commonvoice_locale": "kn", "in_benchmark": true }, { "bcp_47": "pcm", "speakers": 44945880, "language_name": "Nigerian Pidgin", "autonym": "Naijíriá Píjin", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 14.0, "commonvoice_locale": "pcm", "in_benchmark": false }, { "bcp_47": "ml", "speakers": 43257484, "language_name": "Malayalam", "autonym": "മലയാളം", "family": "Dravidian", "flores_path": "mal_Mlym", "fleurs_tag": "ml_in", "commonvoice_hours": 2.8, "commonvoice_locale": "ml", "in_benchmark": true }, { "bcp_47": "or", "speakers": 42434880, "language_name": "Odia", "autonym": "ଓଡ଼ିଆ", "family": "Indo-European", "flores_path": "ory_Orya", "fleurs_tag": "or_in", "commonvoice_hours": 2.8, "commonvoice_locale": "or", "in_benchmark": true }, { "bcp_47": "pl", "speakers": 41077399, "language_name": "Polish", "autonym": "Polski", "family": "Indo-European", "flores_path": "pol_Latn", "fleurs_tag": "pl_pl", "commonvoice_hours": 174.0, "commonvoice_locale": "pl", "in_benchmark": true }, { "bcp_47": "hsn", "speakers": 40426580, "language_name": "Xiang Chinese", "autonym": "Xiang Chinese", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ha", "speakers": 40411882, "language_name": "Hausa", "autonym": "Hausa", "family": "Afro-Asiatic", "flores_path": "hau_Latn", "fleurs_tag": "ha_ng", "commonvoice_hours": 4.1, "commonvoice_locale": "ha", "in_benchmark": true }, { "bcp_47": "sd", "speakers": 40329510, "language_name": "Sindhi", "autonym": "سنڌي", "family": "Indo-European", "flores_path": "snd_Arab", "fleurs_tag": "sd_in", "commonvoice_hours": 0.4, "commonvoice_locale": "sd", "in_benchmark": true }, { "bcp_47": "apc", "speakers": 39031474, "language_name": "North Levantine Arabic", "autonym": "العامية", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ms", "speakers": 38097307, "language_name": "Malay", "autonym": "Bahasa Malaysia", "family": "Austronesian", "flores_path": "zsm_Latn", "fleurs_tag": "ms_my", "commonvoice_hours": 0.0, "commonvoice_locale": "ms", "in_benchmark": true }, { "bcp_47": "my", "speakers": 36559231, "language_name": "Burmese", "autonym": "မြန်မာ", "family": "Sino-Tibetan", "flores_path": "mya_Mymr", "fleurs_tag": "my_mm", "commonvoice_hours": 0.0, "commonvoice_locale": "my", "in_benchmark": true }, { "bcp_47": "am", "speakers": 35728475, "language_name": "Amharic", "autonym": "አማርኛ", "family": "Afro-Asiatic", "flores_path": "amh_Ethi", "fleurs_tag": "am_et", "commonvoice_hours": 1.8, "commonvoice_locale": "am", "in_benchmark": true }, { "bcp_47": "arq", "speakers": 35667507, "language_name": "Algerian Arabic", "autonym": "Algerian Arabic", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "om", "speakers": 34897121, "language_name": "Oromo", "autonym": "Oromoo", "family": "Afro-Asiatic", "flores_path": "gaz_Latn", "fleurs_tag": "om_et", "commonvoice_hours": 0.0, "commonvoice_locale": "om", "in_benchmark": true }, { "bcp_47": "bho", "speakers": 32934797, "language_name": "Bhojpuri", "autonym": "भोजपुरी", "family": "Indo-European", "flores_path": "bho_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "uz", "speakers": 32792780, "language_name": "Uzbek", "autonym": "O‘Zbek", "family": "Turkic", "flores_path": "uzn_Latn", "fleurs_tag": "uz_uz", "commonvoice_hours": 100.0, "commonvoice_locale": "uz", "in_benchmark": true }, { "bcp_47": "az", "speakers": 32446682, "language_name": "Azerbaijani", "autonym": "Azərbaycan", "family": "Turkic", "flores_path": "azj_Latn", "fleurs_tag": "az_az", "commonvoice_hours": 0.5, "commonvoice_locale": "az", "in_benchmark": true }, { "bcp_47": "hak", "speakers": 32062460, "language_name": "Hakka Chinese", "autonym": "Hakka Chinese", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "su", "speakers": 32043120, "language_name": "Sundanese", "autonym": "Basa Sunda", "family": "Austronesian", "flores_path": "sun_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "nl", "speakers": 31765645, "language_name": "Dutch", "autonym": "Nederlands", "family": "Indo-European", "flores_path": "nld_Latn", "fleurs_tag": "nl_nl", "commonvoice_hours": 119.0, "commonvoice_locale": "nl", "in_benchmark": true }, { "bcp_47": "ary", "speakers": 30938679, "language_name": "Moroccan Arabic", "autonym": "Moroccan Arabic", "family": "Afro-Asiatic", "flores_path": "ary_Arab", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "uk", "speakers": 29348975, "language_name": "Ukrainian", "autonym": "Українська", "family": "Indo-European", "flores_path": "ukr_Cyrl", "fleurs_tag": "uk_ua", "commonvoice_hours": 99.0, "commonvoice_locale": "uk", "in_benchmark": true }, { "bcp_47": "yo", "speakers": 28685568, "language_name": "Yoruba", "autonym": "Èdè Yorùbá", "family": "Atlantic-Congo", "flores_path": "yor_Latn", "fleurs_tag": "yo_ng", "commonvoice_hours": 6.1, "commonvoice_locale": "yo", "in_benchmark": true }, { "bcp_47": "skr", "speakers": 28020120, "language_name": "Saraiki", "autonym": "سرائیکی", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 4.3, "commonvoice_locale": "skr", "in_benchmark": false }, { "bcp_47": "ig", "speakers": 27823640, "language_name": "Igbo", "autonym": "Igbo", "family": "Atlantic-Congo", "flores_path": "ibo_Latn", "fleurs_tag": "ig_ng", "commonvoice_hours": 0.0, "commonvoice_locale": "ig", "in_benchmark": true }, { "bcp_47": "nan", "speakers": 26486380, "language_name": "Min Nan Chinese", "autonym": "Min Nan Chinese", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ceb", "speakers": 26203440, "language_name": "Cebuano", "autonym": "Cebuano", "family": "Austronesian", "flores_path": "ceb_Latn", "fleurs_tag": "ceb_ph", "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "awa", "speakers": 25862924, "language_name": "Awadhi", "autonym": "Awadhi", "family": "Indo-European", "flores_path": "awa_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "mg", "speakers": 24260130, "language_name": "Malagasy", "autonym": "Malagasy", "family": "Austronesian", "flores_path": "plt_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "mg", "in_benchmark": true }, { "bcp_47": "gan", "speakers": 23698340, "language_name": "Gan Chinese", "autonym": "Gan Chinese", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ro", "speakers": 22187408, "language_name": "Romanian", "autonym": "Română", "family": "Indo-European", "flores_path": "ron_Latn", "fleurs_tag": "ro_ro", "commonvoice_hours": 21.0, "commonvoice_locale": "ro", "in_benchmark": true }, { "bcp_47": "bar", "speakers": 22043627, "language_name": "Bavarian", "autonym": "Bavarian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ne", "speakers": 20903374, "language_name": "Nepali", "autonym": "नेपाली", "family": "Indo-European", "flores_path": "npi_Deva", "fleurs_tag": "ne_np", "commonvoice_hours": 1.3, "commonvoice_locale": "ne-NP", "in_benchmark": true }, { "bcp_47": "mai", "speakers": 19249149, "language_name": "Maithili", "autonym": "मैथिली", "family": "Indo-European", "flores_path": "mai_Deva", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "mai", "in_benchmark": true }, { "bcp_47": "as", "speakers": 17239170, "language_name": "Assamese", "autonym": "অসমীয়া", "family": "Indo-European", "flores_path": "asm_Beng", "fleurs_tag": "as_in", "commonvoice_hours": 2.8, "commonvoice_locale": "as", "in_benchmark": true }, { "bcp_47": "ny", "speakers": 17026781, "language_name": "Nyanja", "autonym": "Nyanja", "family": "Atlantic-Congo", "flores_path": "nya_Latn", "fleurs_tag": "ny_mw", "commonvoice_hours": 0.0, "commonvoice_locale": "ny", "in_benchmark": true }, { "bcp_47": "so", "speakers": 16911645, "language_name": "Somali", "autonym": "Soomaali", "family": "Afro-Asiatic", "flores_path": "som_Latn", "fleurs_tag": "so_so", "commonvoice_hours": 0.0, "commonvoice_locale": "so", "in_benchmark": true }, { "bcp_47": "mad", "speakers": 16822638, "language_name": "Madurese", "autonym": "Madurese", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tts", "speakers": 16554576, "language_name": "Northeastern Thai", "autonym": "Northeastern Thai", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rkt", "speakers": 16274502, "language_name": "Rangpuri", "autonym": "Rangpuri", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mag", "speakers": 15913080, "language_name": "Magahi", "autonym": "Magahi", "family": "Indo-European", "flores_path": "mag_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "bgc", "speakers": 15913080, "language_name": "Haryanvi", "autonym": "हरियाणवी", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mwr", "speakers": 15913080, "language_name": "Marwari", "autonym": "Marwari", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sr", "speakers": 15602410, "language_name": "Serbian", "autonym": "Српски", "family": "Indo-European", "flores_path": "srp_Cyrl", "fleurs_tag": "sr_rs", "commonvoice_hours": 7.5, "commonvoice_locale": "sr", "in_benchmark": true }, { "bcp_47": "si", "speakers": 15564656, "language_name": "Sinhala", "autonym": "සිංහල", "family": "Indo-European", "flores_path": "sin_Sinh", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "si", "in_benchmark": true }, { "bcp_47": "km", "speakers": 15065030, "language_name": "Khmer", "autonym": "ខ្មែរ", "family": "Austroasiatic", "flores_path": "khm_Khmr", "fleurs_tag": "km_kh", "commonvoice_hours": 0.0, "commonvoice_locale": "km", "in_benchmark": true }, { "bcp_47": "hne", "speakers": 14586990, "language_name": "Chhattisgarhi", "autonym": "Chhattisgarhi", "family": "Indo-European", "flores_path": "hne_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "fuv", "speakers": 14339876, "language_name": "Nigerian Fulfulde", "autonym": "Nigerian Fulfulde", "family": "Atlantic-Congo", "flores_path": "fuv_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "zu", "speakers": 13973830, "language_name": "Zulu", "autonym": "Isizulu", "family": "Atlantic-Congo", "flores_path": "zul_Latn", "fleurs_tag": "zu_za", "commonvoice_hours": 0.0, "commonvoice_locale": "zu", "in_benchmark": true }, { "bcp_47": "kk", "speakers": 13637392, "language_name": "Kazakh", "autonym": "Қазақ Тілі", "family": "Turkic", "flores_path": "kaz_Cyrl", "fleurs_tag": "kk_kz", "commonvoice_hours": 2.1, "commonvoice_locale": "kk", "in_benchmark": true }, { "bcp_47": "dcc", "speakers": 13128291, "language_name": "Deccan", "autonym": "Deccan", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cs", "speakers": 13045532, "language_name": "Czech", "autonym": "Čeština", "family": "Indo-European", "flores_path": "ces_Latn", "fleurs_tag": "cs_cz", "commonvoice_hours": 75.0, "commonvoice_locale": "cs", "in_benchmark": true }, { "bcp_47": "sv", "speakers": 12932871, "language_name": "Swedish", "autonym": "Svenska", "family": "Indo-European", "flores_path": "swe_Latn", "fleurs_tag": "sv_se", "commonvoice_hours": 47.0, "commonvoice_locale": "sv-SE", "in_benchmark": true }, { "bcp_47": "hu", "speakers": 12443430, "language_name": "Hungarian", "autonym": "Magyar", "family": "Uralic", "flores_path": "hun_Latn", "fleurs_tag": "hu_hu", "commonvoice_hours": 92.0, "commonvoice_locale": "hu", "in_benchmark": true }, { "bcp_47": "el", "speakers": 12292242, "language_name": "Greek", "autonym": "Ελληνικά", "family": "Indo-European", "flores_path": "ell_Grek", "fleurs_tag": "el_gr", "commonvoice_hours": 20.0, "commonvoice_locale": "el", "in_benchmark": true }, { "bcp_47": "sn", "speakers": 11782503, "language_name": "Shona", "autonym": "Chishona", "family": "Atlantic-Congo", "flores_path": "sna_Latn", "fleurs_tag": "sn_zw", "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "nds", "speakers": 11520008, "language_name": "Low German", "autonym": "Neddersass’Sch", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ak", "speakers": 11442678, "language_name": "Akan", "autonym": "Akan", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.2, "commonvoice_locale": "tw", "in_benchmark": false }, { "bcp_47": "qu", "speakers": 11385851, "language_name": "Quechua", "autonym": "Runasimi", "family": "Quechuan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ckb", "speakers": 11086549, "language_name": "Central Kurdish", "autonym": "کوردیی ناوەندی", "family": "Indo-European", "flores_path": "ckb_Arab", "fleurs_tag": "ckb_iq", "commonvoice_hours": 135.0, "commonvoice_locale": "ckb", "in_benchmark": true }, { "bcp_47": "rw", "speakers": 11083625, "language_name": "Kinyarwanda", "autonym": "Kinyarwanda", "family": "Atlantic-Congo", "flores_path": "kin_Latn", "fleurs_tag": null, "commonvoice_hours": 2002.0, "commonvoice_locale": "rw", "in_benchmark": true }, { "bcp_47": "wo", "speakers": 11025494, "language_name": "Wolof", "autonym": "Wolof", "family": "Atlantic-Congo", "flores_path": "wol_Latn", "fleurs_tag": "wo_sn", "commonvoice_hours": 0.0, "commonvoice_locale": "wo", "in_benchmark": true }, { "bcp_47": "aeb", "speakers": 10549080, "language_name": "Tunisian Arabic", "autonym": "Tunisian Arabic", "family": "Afro-Asiatic", "flores_path": "aeb_Arab", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "ilo", "speakers": 10481376, "language_name": "Iloko", "autonym": "Ilokano", "family": "Austronesian", "flores_path": "ilo_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "xh", "speakers": 10182944, "language_name": "Xhosa", "autonym": "Isixhosa", "family": "Atlantic-Congo", "flores_path": "xho_Latn", "fleurs_tag": "xh_za", "commonvoice_hours": 0.0, "commonvoice_locale": "xh", "in_benchmark": true }, { "bcp_47": "ti", "speakers": 10145911, "language_name": "Tigrinya", "autonym": "ትግርኛ", "family": "Afro-Asiatic", "flores_path": "tir_Ethi", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ti", "in_benchmark": true }, { "bcp_47": "be", "speakers": 10064517, "language_name": "Belarusian", "autonym": "Беларуская", "family": "Indo-European", "flores_path": "bel_Cyrl", "fleurs_tag": "be_by", "commonvoice_hours": 1806.0, "commonvoice_locale": "be", "in_benchmark": true }, { "bcp_47": "lua", "speakers": 9770880, "language_name": "Luba-Lulua", "autonym": "Luba-Lulua", "family": "Atlantic-Congo", "flores_path": "lua_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "lua", "in_benchmark": true }, { "bcp_47": "tg", "speakers": 9644223, "language_name": "Tajik", "autonym": "Тоҷикӣ", "family": "Indo-European", "flores_path": "tgk_Cyrl", "fleurs_tag": "tg_tj", "commonvoice_hours": 0.0, "commonvoice_locale": "tg", "in_benchmark": true }, { "bcp_47": "umb", "speakers": 9431467, "language_name": "Umbundu", "autonym": "Umbundu", "family": "Atlantic-Congo", "flores_path": "umb_Latn", "fleurs_tag": "umb_ao", "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "bm", "speakers": 9385632, "language_name": "Bambara", "autonym": "Bamanakan", "family": "Mande", "flores_path": "bam_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "bm", "in_benchmark": true }, { "bcp_47": "af", "speakers": 9318845, "language_name": "Afrikaans", "autonym": "Afrikaans", "family": "Indo-European", "flores_path": "afr_Latn", "fleurs_tag": "af_za", "commonvoice_hours": 0.5, "commonvoice_locale": "af", "in_benchmark": true }, { "bcp_47": "hil", "speakers": 9171204, "language_name": "Hiligaynon", "autonym": "Ilonggo", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "hil", "in_benchmark": false }, { "bcp_47": "ki", "speakers": 9099743, "language_name": "Kikuyu", "autonym": "Gikuyu", "family": "Atlantic-Congo", "flores_path": "kik_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ki", "in_benchmark": true }, { "bcp_47": "ht", "speakers": 8964918, "language_name": "Haitian Creole", "autonym": "Haitian Creole", "family": "Indo-European", "flores_path": "hat_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ht", "in_benchmark": true }, { "bcp_47": "ca", "speakers": 8679139, "language_name": "Catalan", "autonym": "Català", "family": "Indo-European", "flores_path": "cat_Latn", "fleurs_tag": "ca_es", "commonvoice_hours": 2854.0, "commonvoice_locale": "ca", "in_benchmark": true }, { "bcp_47": "he", "speakers": 8675480, "language_name": "Hebrew", "autonym": "עברית", "family": "Afro-Asiatic", "flores_path": "heb_Hebr", "fleurs_tag": "he_il", "commonvoice_hours": 1.2, "commonvoice_locale": "he", "in_benchmark": true }, { "bcp_47": "ii", "speakers": 8364120, "language_name": "Sichuan Yi", "autonym": "ꆈꌠꉙ", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mos", "speakers": 8334160, "language_name": "Mossi", "autonym": "Mossi", "family": "Atlantic-Congo", "flores_path": "mos_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "mos", "in_benchmark": true }, { "bcp_47": "bal", "speakers": 8227887, "language_name": "Baluchi", "autonym": "بلۆچی", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "bal", "in_benchmark": false }, { "bcp_47": "syl", "speakers": 8132550, "language_name": "Sylheti", "autonym": "Sylheti", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kmb", "speakers": 8130575, "language_name": "Kimbundu", "autonym": "Kimbundu", "family": "Atlantic-Congo", "flores_path": "kmb_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "ug", "speakers": 8052967, "language_name": "Uyghur", "autonym": "ئۇيغۇرچە", "family": "Turkic", "flores_path": "uig_Arab", "fleurs_tag": null, "commonvoice_hours": 369.0, "commonvoice_locale": "ug", "in_benchmark": true }, { "bcp_47": "min", "speakers": 8010780, "language_name": "Minangkabau", "autonym": "Minangkabau", "family": "Austronesian", "flores_path": "min_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "gsw", "speakers": 7956952, "language_name": "Swiss German", "autonym": "Schwiizertüütsch", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "gsw", "in_benchmark": false }, { "bcp_47": "bg", "speakers": 7878315, "language_name": "Bulgarian", "autonym": "Български", "family": "Indo-European", "flores_path": "bul_Cyrl", "fleurs_tag": "bg_bg", "commonvoice_hours": 16.0, "commonvoice_locale": "bg", "in_benchmark": true }, { "bcp_47": "zgh", "speakers": 7823574, "language_name": "Standard Moroccan Tamazight", "autonym": "ⵜⴰⵎⴰⵣⵉⵖⵜ", "family": "Afro-Asiatic", "flores_path": "zgh_Tfng", "fleurs_tag": null, "commonvoice_hours": 1.3, "commonvoice_locale": "zgh", "in_benchmark": true }, { "bcp_47": "ff", "speakers": 7788904, "language_name": "Fula", "autonym": "Pulaar", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": "ff_sn", "commonvoice_hours": 0.0, "commonvoice_locale": "ff", "in_benchmark": false }, { "bcp_47": "bs", "speakers": 7594468, "language_name": "Bosnian", "autonym": "Bosanski", "family": "Indo-European", "flores_path": "bos_Latn", "fleurs_tag": "bs_ba", "commonvoice_hours": 0.0, "commonvoice_locale": "bs", "in_benchmark": true }, { "bcp_47": "rn", "speakers": 7475454, "language_name": "Rundi", "autonym": "Ikirundi", "family": "Atlantic-Congo", "flores_path": "run_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "rn", "in_benchmark": true }, { "bcp_47": "bjj", "speakers": 7426104, "language_name": "Kanauji", "autonym": "Kanauji", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sat", "speakers": 7293495, "language_name": "Santali", "autonym": "ᱥᱟᱱᱛᱟᱲᱤ", "family": "Austroasiatic", "flores_path": "sat_Olck", "fleurs_tag": null, "commonvoice_hours": 0.5, "commonvoice_locale": "sat", "in_benchmark": true }, { "bcp_47": "da", "speakers": 7072056, "language_name": "Danish", "autonym": "Dansk", "family": "Indo-European", "flores_path": "dan_Latn", "fleurs_tag": "da_dk", "commonvoice_hours": 13.0, "commonvoice_locale": "da", "in_benchmark": true }, { "bcp_47": "tk", "speakers": 6870838, "language_name": "Turkmen", "autonym": "Türkmen Dili", "family": "Turkic", "flores_path": "tuk_Latn", "fleurs_tag": null, "commonvoice_hours": 2.8, "commonvoice_locale": "tk", "in_benchmark": true }, { "bcp_47": "ku", "speakers": 6866757, "language_name": "Kurdish", "autonym": "Kurdî (Kurmancî)", "family": "Indo-European", "flores_path": "kmr_Latn", "fleurs_tag": null, "commonvoice_hours": 69.0, "commonvoice_locale": "kmr", "in_benchmark": true }, { "bcp_47": "hr", "speakers": 6813164, "language_name": "Croatian", "autonym": "Hrvatski", "family": "Indo-European", "flores_path": "hrv_Latn", "fleurs_tag": "hr_hr", "commonvoice_hours": 0.0, "commonvoice_locale": "hr", "in_benchmark": true }, { "bcp_47": "sq", "speakers": 6791906, "language_name": "Albanian", "autonym": "Shqip", "family": "Indo-European", "flores_path": "als_Latn", "fleurs_tag": null, "commonvoice_hours": 8.8, "commonvoice_locale": "sq", "in_benchmark": true }, { "bcp_47": "sk", "speakers": 6680269, "language_name": "Slovak", "autonym": "Slovenčina", "family": "Indo-European", "flores_path": "slk_Latn", "fleurs_tag": "sk_sk", "commonvoice_hours": 48.0, "commonvoice_locale": "sk", "in_benchmark": true }, { "bcp_47": "dyu", "speakers": 6667328, "language_name": "Dyula", "autonym": "Dyula", "family": "Mande", "flores_path": "dyu_Latn", "fleurs_tag": null, "commonvoice_hours": 0.4, "commonvoice_locale": "dyu", "in_benchmark": true }, { "bcp_47": "nod", "speakers": 6621830, "language_name": "Northern Thai", "autonym": "Northern Thai", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mn", "speakers": 6572846, "language_name": "Mongolian", "autonym": "Монгол", "family": "Mongolic-Khitan", "flores_path": "khk_Cyrl", "fleurs_tag": "mn_mn", "commonvoice_hours": 46.0, "commonvoice_locale": "mn", "in_benchmark": true }, { "bcp_47": "st", "speakers": 6390567, "language_name": "Southern Sotho", "autonym": "Sesotho", "family": "Atlantic-Congo", "flores_path": "sot_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "st", "in_benchmark": true }, { "bcp_47": "kri", "speakers": 6293684, "language_name": "Krio", "autonym": "Krio", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "shi", "speakers": 6187736, "language_name": "Tachelhit", "autonym": "ⵜⴰⵛⵍⵃⵉⵜ", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "shi", "in_benchmark": false }, { "bcp_47": "tn", "speakers": 6113428, "language_name": "Tswana", "autonym": "Tswana", "family": "Atlantic-Congo", "flores_path": "tsn_Latn", "fleurs_tag": null, "commonvoice_hours": 4.2, "commonvoice_locale": "tn", "in_benchmark": true }, { "bcp_47": "wtm", "speakers": 6100014, "language_name": "Mewati", "autonym": "Mewati", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "luy", "speakers": 5888069, "language_name": "Luyia", "autonym": "Luluhia", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "bxk", "in_benchmark": false }, { "bcp_47": "gn", "speakers": 5827107, "language_name": "Guarani", "autonym": "Avañe’Ẽ", "family": "Tupian", "flores_path": "gug_Latn", "fleurs_tag": null, "commonvoice_hours": 3.7, "commonvoice_locale": "gn", "in_benchmark": true }, { "bcp_47": "fi", "speakers": 5736842, "language_name": "Finnish", "autonym": "Suomi", "family": "Uralic", "flores_path": "fin_Latn", "fleurs_tag": "fi_fi", "commonvoice_hours": 15.0, "commonvoice_locale": "fi", "in_benchmark": true }, { "bcp_47": "lg", "speakers": 5622890, "language_name": "Ganda", "autonym": "Luganda", "family": "Atlantic-Congo", "flores_path": "lug_Latn", "fleurs_tag": "lg_ug", "commonvoice_hours": 437.0, "commonvoice_locale": "lg", "in_benchmark": true }, { "bcp_47": "bew", "speakers": 5607546, "language_name": "Betawi", "autonym": "Betawi", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "bew", "in_benchmark": false }, { "bcp_47": "ks", "speakers": 5598085, "language_name": "Kashmiri", "autonym": "کٲشُر", "family": "Indo-European", "flores_path": "kas_Arab", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ks", "in_benchmark": true }, { "bcp_47": "sou", "speakers": 5518192, "language_name": "Southern Thai", "autonym": "Southern Thai", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nb", "speakers": 5468932, "language_name": "Norwegian Bokmål", "autonym": "Norsk Bokmål", "family": "Indo-European", "flores_path": "nob_Latn", "fleurs_tag": "nb_no", "commonvoice_hours": 0.3, "commonvoice_locale": "nb-NO", "in_benchmark": true }, { "bcp_47": "no", "speakers": 5467440, "language_name": "Norwegian", "autonym": "Norsk", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bem", "speakers": 5402246, "language_name": "Bemba", "autonym": "Ichibemba", "family": "Atlantic-Congo", "flores_path": "bem_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "hy", "speakers": 5317273, "language_name": "Armenian", "autonym": "Հայերեն", "family": "Indo-European", "flores_path": "hye_Armn", "fleurs_tag": "hy_am", "commonvoice_hours": 31.0, "commonvoice_locale": "hy-AM", "in_benchmark": true }, { "bcp_47": "nso", "speakers": 5307578, "language_name": "Northern Sotho", "autonym": "Northern Sotho", "family": "Atlantic-Congo", "flores_path": "nso_Latn", "fleurs_tag": "nso_za", "commonvoice_hours": 0.0, "commonvoice_locale": "nso", "in_benchmark": true }, { "bcp_47": "luo", "speakers": 5245734, "language_name": "Luo (Kenya and Tanzania)", "autonym": "Dholuo", "family": "Nilotic", "flores_path": "luo_Latn", "fleurs_tag": "luo_ke", "commonvoice_hours": 30.0, "commonvoice_locale": "luo", "in_benchmark": true }, { "bcp_47": "tpi", "speakers": 5154217, "language_name": "Tok Pisin", "autonym": "Tok Pisin", "family": "Indo-European", "flores_path": "tpi_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "lo", "speakers": 5138706, "language_name": "Lao", "autonym": "ລາວ", "family": "Tai-Kadai", "flores_path": "lao_Laoo", "fleurs_tag": "lo_la", "commonvoice_hours": 0.3, "commonvoice_locale": "lo", "in_benchmark": true }, { "bcp_47": "suk", "speakers": 5094094, "language_name": "Sukuma", "autonym": "Sukuma", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kok", "speakers": 4906533, "language_name": "Konkani", "autonym": "कोंकणी", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "knn", "in_benchmark": false }, { "bcp_47": "ts", "speakers": 4880932, "language_name": "Tsonga", "autonym": "Tsonga", "family": "Atlantic-Congo", "flores_path": "tso_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ts", "in_benchmark": true }, { "bcp_47": "vmf", "speakers": 4809582, "language_name": "Main-Franconian", "autonym": "Main-Franconian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ban", "speakers": 4806468, "language_name": "Balinese", "autonym": "Balinese", "family": "Austronesian", "flores_path": "ban_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "ee", "speakers": 4690857, "language_name": "Ewe", "autonym": "Eʋegbe", "family": "Atlantic-Congo", "flores_path": "ewe_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ee", "in_benchmark": true }, { "bcp_47": "za", "speakers": 4321462, "language_name": "Zhuang", "autonym": "Vahcuengh", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bug", "speakers": 4298211, "language_name": "Buginese", "autonym": "Buginese", "family": "Austronesian", "flores_path": "bug_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "mzn", "speakers": 4246165, "language_name": "Mazanderani", "autonym": "مازرونی", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gom", "speakers": 4243488, "language_name": "Goan Konkani", "autonym": "Goan Konkani", "family": "Indo-European", "flores_path": "gom_Deva", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "gom", "in_benchmark": true }, { "bcp_47": "kam", "speakers": 4068120, "language_name": "Kamba", "autonym": "Kikamba", "family": "Atlantic-Congo", "flores_path": "kam_Latn", "fleurs_tag": "kam_ke", "commonvoice_hours": 0.0, "commonvoice_locale": "kam", "in_benchmark": true }, { "bcp_47": "kln", "speakers": 4068120, "language_name": "Kalenjin", "autonym": "Kalenjin", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 43.0, "commonvoice_locale": "kln", "in_benchmark": false }, { "bcp_47": "bjn", "speakers": 4010288, "language_name": "Banjar", "autonym": "Banjar", "family": "Austronesian", "flores_path": "bjn_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "hno", "speakers": 3969517, "language_name": "Northern Hindko", "autonym": "Northern Hindko", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "hno", "in_benchmark": false }, { "bcp_47": "vmw", "speakers": 3912766, "language_name": "Makhuwa", "autonym": "Emakhuwa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "vmw", "in_benchmark": false }, { "bcp_47": "glk", "speakers": 3906472, "language_name": "Gilaki", "autonym": "Gilaki", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lmo", "speakers": 3901518, "language_name": "Lombard", "autonym": "Lombard", "family": "Indo-European", "flores_path": "lmo_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "dje", "speakers": 3871308, "language_name": "Zarma", "autonym": "Zarmaciine", "family": "Songhay", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ndc", "speakers": 3867046, "language_name": "Ndau", "autonym": "Ndau", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sid", "speakers": 3783955, "language_name": "Sidamo", "autonym": "Sidamo", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ace", "speakers": 3738364, "language_name": "Achinese", "autonym": "Achinese", "family": "Austronesian", "flores_path": "ace_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ace", "in_benchmark": true }, { "bcp_47": "swv", "speakers": 3713052, "language_name": "Shekhawati", "autonym": "Shekhawati", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rif", "speakers": 3692411, "language_name": "Riffian", "autonym": "Tarifit", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "rif", "in_benchmark": false }, { "bcp_47": "shn", "speakers": 3687984, "language_name": "Shan", "autonym": "တႆး", "family": "Tai-Kadai", "flores_path": "shn_Mymr", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "shn", "in_benchmark": true }, { "bcp_47": "lmn", "speakers": 3580443, "language_name": "Lambadi", "autonym": "Lambadi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gbm", "speakers": 3580443, "language_name": "Garhwali", "autonym": "Garhwali", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ka", "speakers": 3543646, "language_name": "Georgian", "autonym": "ქართული", "family": "Kartvelian", "flores_path": "kat_Geor", "fleurs_tag": "ka_ge", "commonvoice_hours": 164.0, "commonvoice_locale": "ka", "in_benchmark": true }, { "bcp_47": "gl", "speakers": 3515530, "language_name": "Galician", "autonym": "Galego", "family": "Indo-European", "flores_path": "glg_Latn", "fleurs_tag": "gl_es", "commonvoice_hours": 115.0, "commonvoice_locale": "gl", "in_benchmark": true }, { "bcp_47": "ln", "speakers": 3514491, "language_name": "Lingala", "autonym": "Lingála", "family": "Atlantic-Congo", "flores_path": "lin_Latn", "fleurs_tag": "ln_cd", "commonvoice_hours": 0.0, "commonvoice_locale": "ln", "in_benchmark": true }, { "bcp_47": "man", "speakers": 3511762, "language_name": "Mandingo", "autonym": "Mandingo", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tzm", "speakers": 3485047, "language_name": "Central Atlas Tamazight", "autonym": "Tamaziɣt N Laṭlaṣ", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mfa", "speakers": 3448870, "language_name": "Pattani Malay", "autonym": "Pattani Malay", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tiv", "speakers": 3424448, "language_name": "Tiv", "autonym": "Tiv", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kab", "speakers": 3351886, "language_name": "Kabyle", "autonym": "Taqbaylit", "family": "Afro-Asiatic", "flores_path": "kab_Latn", "fleurs_tag": null, "commonvoice_hours": 571.0, "commonvoice_locale": "kab", "in_benchmark": true }, { "bcp_47": "ky", "speakers": 3338267, "language_name": "Kyrgyz", "autonym": "Кыргызча", "family": "Turkic", "flores_path": "kir_Cyrl", "fleurs_tag": "ky_kg", "commonvoice_hours": 39.0, "commonvoice_locale": "ky", "in_benchmark": true }, { "bcp_47": "bik", "speakers": 3275430, "language_name": "Bikol", "autonym": "Bikol", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fon", "speakers": 3216150, "language_name": "Fon", "autonym": "Fon", "family": "Atlantic-Congo", "flores_path": "fon_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "gon", "speakers": 3182616, "language_name": "Gondi", "autonym": "Gondi", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "war", "speakers": 3166927, "language_name": "Waray", "autonym": "Waray", "family": "Austronesian", "flores_path": "war_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "sdh", "speakers": 3142162, "language_name": "Southern Kurdish", "autonym": "کوردی خوارگ", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "sdh", "in_benchmark": false }, { "bcp_47": "brh", "speakers": 3035513, "language_name": "Brahui", "autonym": "Brahui", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bci", "speakers": 3022921, "language_name": "Baoulé", "autonym": "Baoulé", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 2.1, "commonvoice_locale": "bci", "in_benchmark": false }, { "bcp_47": "bo", "speakers": 3006697, "language_name": "Tibetan", "autonym": "བོད་སྐད་", "family": "Sino-Tibetan", "flores_path": "bod_Tibt", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "bo", "in_benchmark": true }, { "bcp_47": "ibb", "speakers": 2996392, "language_name": "Ibibio", "autonym": "Ibibio", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 2.7, "commonvoice_locale": "ibb", "in_benchmark": false }, { "bcp_47": "efi", "speakers": 2996392, "language_name": "Efik", "autonym": "Efik", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sg", "speakers": 2935521, "language_name": "Sango", "autonym": "Sängö", "family": "Atlantic-Congo", "flores_path": "sag_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "kfy", "speakers": 2917398, "language_name": "Kumaoni", "autonym": "Kumaoni", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ay", "speakers": 2838620, "language_name": "Aymara", "autonym": "Aymara", "family": "Aymaran", "flores_path": "ayr_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "nyn", "speakers": 2724939, "language_name": "Nyankole", "autonym": "Runyankore", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "nyn", "in_benchmark": false }, { "bcp_47": "jam", "speakers": 2668142, "language_name": "Jamaican Creole English", "autonym": "Jamaican Creole English", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "jam", "in_benchmark": false }, { "bcp_47": "doi", "speakers": 2652180, "language_name": "Dogri", "autonym": "डोगरी", "family": "Indo-European", "flores_path": "dgo_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "guz", "speakers": 2622867, "language_name": "Gusii", "autonym": "Ekegusii", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sas", "speakers": 2590152, "language_name": "Sasak", "autonym": "Sasak", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kru", "speakers": 2519571, "language_name": "Kurukh", "autonym": "Kurukh", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pam", "speakers": 2511163, "language_name": "Pampanga", "autonym": "Pampanga", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fbl", "speakers": 2511163, "language_name": "West Albay Bikol", "autonym": "West Albay Bikol", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lt", "speakers": 2488617, "language_name": "Lithuanian", "autonym": "Lietuvių", "family": "Indo-European", "flores_path": "lit_Latn", "fleurs_tag": "lt_lt", "commonvoice_hours": 25.0, "commonvoice_locale": "lt", "in_benchmark": true }, { "bcp_47": "bej", "speakers": 2460326, "language_name": "Beja", "autonym": "Beja", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bbc", "speakers": 2456639, "language_name": "Batak Toba", "autonym": "Batak Toba", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sck", "speakers": 2386962, "language_name": "Sadri", "autonym": "Sadri", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wbq", "speakers": 2386962, "language_name": "Waddar", "autonym": "Waddar", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lu", "speakers": 2340940, "language_name": "Luba-Katanga", "autonym": "Tshiluba", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cgg", "speakers": 2335662, "language_name": "Chiga", "autonym": "Rukiga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "cgg", "in_benchmark": false }, { "bcp_47": "xog", "speakers": 2292409, "language_name": "Soga", "autonym": "Olusoga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ss", "speakers": 2212379, "language_name": "Swati", "autonym": "Siswati", "family": "Atlantic-Congo", "flores_path": "ssw_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ss", "in_benchmark": true }, { "bcp_47": "haz", "speakers": 2161984, "language_name": "Hazaragi", "autonym": "Hazaragi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mer", "speakers": 2141116, "language_name": "Meru", "autonym": "Kĩmĩrũ", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "xnr", "speakers": 2121744, "language_name": "Kangri", "autonym": "कांगड़ी", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "aa", "speakers": 2119663, "language_name": "Afar", "autonym": "Afar", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "aa", "in_benchmark": false }, { "bcp_47": "teo", "speakers": 2082973, "language_name": "Teso", "autonym": "Kiteso", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ngl", "speakers": 2046678, "language_name": "Lomwe", "autonym": "Lomwe", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "oc", "speakers": 2040398, "language_name": "Occitan", "autonym": "Occitan", "family": "Indo-European", "flores_path": "oci_Latn", "fleurs_tag": "oc_fr", "commonvoice_hours": 1.8, "commonvoice_locale": "oc", "in_benchmark": true }, { "bcp_47": "bgn", "speakers": 2037382, "language_name": "Western Balochi", "autonym": "بلوچی (رخشانی)", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lrc", "speakers": 2020512, "language_name": "Northern Luri", "autonym": "لۊری شومالی", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wbr", "speakers": 1989135, "language_name": "Wagdi", "autonym": "Wagdi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tcy", "speakers": 1989135, "language_name": "Tulu", "autonym": "Tulu", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "khn", "speakers": 1989135, "language_name": "Khandesi", "autonym": "Khandesi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tt", "speakers": 1984108, "language_name": "Tatar", "autonym": "Татар", "family": "Turkic", "flores_path": "tat_Cyrl", "fleurs_tag": null, "commonvoice_hours": 32.0, "commonvoice_locale": "tt", "in_benchmark": true }, { "bcp_47": "sl", "speakers": 1973181, "language_name": "Slovenian", "autonym": "Slovenščina", "family": "Indo-European", "flores_path": "slv_Latn", "fleurs_tag": "sl_si", "commonvoice_hours": 18.0, "commonvoice_locale": "sl", "in_benchmark": true }, { "bcp_47": "mak", "speakers": 1949290, "language_name": "Makasar", "autonym": "Makasar", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wal", "speakers": 1946034, "language_name": "Wolaytta", "autonym": "Wolaytta", "family": "Ta-Ne-Omotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nym", "speakers": 1932242, "language_name": "Nyamwezi", "autonym": "Nyamwezi", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "brx", "speakers": 1856526, "language_name": "Bodo", "autonym": "बर’", "family": "Sino-Tibetan", "flores_path": "brx_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "ljp", "speakers": 1842479, "language_name": "Lampung Api", "autonym": "Lampung Api", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cv", "speakers": 1842386, "language_name": "Chuvash", "autonym": "Чӑваш", "family": "Turkic", "flores_path": "chv_Cyrl", "fleurs_tag": null, "commonvoice_hours": 27.0, "commonvoice_locale": "cv", "in_benchmark": true }, { "bcp_47": "ba", "speakers": 1842386, "language_name": "Bashkir", "autonym": "Башҡорт Теле", "family": "Turkic", "flores_path": "bak_Cyrl", "fleurs_tag": null, "commonvoice_hours": 259.0, "commonvoice_locale": "ba", "in_benchmark": true }, { "bcp_47": "rhg", "speakers": 1824082, "language_name": "Rohingya", "autonym": "𐴌𐴗𐴥𐴝𐴙𐴚𐴒𐴙𐴝", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "men", "speakers": 1813083, "language_name": "Mende", "autonym": "Mende", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tum", "speakers": 1780514, "language_name": "Tumbuka", "autonym": "Tumbuka", "family": "Atlantic-Congo", "flores_path": "tum_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "tmh", "speakers": 1776965, "language_name": "Tamashek", "autonym": "Tamashek", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nd", "speakers": 1745556, "language_name": "North Ndebele", "autonym": "Isindebele", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "nd", "in_benchmark": false }, { "bcp_47": "mas", "speakers": 1734738, "language_name": "Masai", "autonym": "Maa", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "srr", "speakers": 1731004, "language_name": "Serer", "autonym": "Serer", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "noe", "speakers": 1723917, "language_name": "Nimadi", "autonym": "Nimadi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tem", "speakers": 1722482, "language_name": "Timne", "autonym": "Timne", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sco", "speakers": 1644028, "language_name": "Scots", "autonym": "Scots", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "sco", "in_benchmark": false }, { "bcp_47": "laj", "speakers": 1643614, "language_name": "Lango (Uganda)", "autonym": "Lango (Uganda)", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rmt", "speakers": 1613543, "language_name": "Domari", "autonym": "Domari", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mk", "speakers": 1608565, "language_name": "Macedonian", "autonym": "Македонски", "family": "Indo-European", "flores_path": "mkd_Cyrl", "fleurs_tag": "mk_mk", "commonvoice_hours": 19.0, "commonvoice_locale": "mk", "in_benchmark": true }, { "bcp_47": "ach", "speakers": 1600361, "language_name": "Acoli", "autonym": "Acoli", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fuq", "speakers": 1594068, "language_name": "Central-Eastern Niger Fulfulde", "autonym": "Central-Eastern Niger Fulfulde", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bhb", "speakers": 1591308, "language_name": "Bhili", "autonym": "Bhili", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pag", "speakers": 1528534, "language_name": "Pangasinan", "autonym": "Pangasinan", "family": "Austronesian", "flores_path": "pag_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "kg", "speakers": 1526700, "language_name": "Kongo", "autonym": "Kongo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bin", "speakers": 1519599, "language_name": "Bini", "autonym": "Bini", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ffm", "speakers": 1505612, "language_name": "Maasina Fulfulde", "autonym": "Maasina Fulfulde", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mni", "speakers": 1476591, "language_name": "Manipuri", "autonym": "মৈতৈলোন্", "family": "Sino-Tibetan", "flores_path": "mni_Beng", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "mni", "in_benchmark": true }, { "bcp_47": "abr", "speakers": 1467010, "language_name": "Abron", "autonym": "Abron", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kde", "speakers": 1463820, "language_name": "Makonde", "autonym": "Chimakonde", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "aln", "speakers": 1430250, "language_name": "Gheg Albanian", "autonym": "Gheg Albanian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "aln", "in_benchmark": false }, { "bcp_47": "ve", "speakers": 1391759, "language_name": "Venda", "autonym": "Tshivenḓa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ve", "in_benchmark": false }, { "bcp_47": "seh", "speakers": 1384517, "language_name": "Sena", "autonym": "Sena", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "vec", "speakers": 1380829, "language_name": "Venetian", "autonym": "Veneto", "family": "Indo-European", "flores_path": "vec_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "vec", "in_benchmark": true }, { "bcp_47": "sus", "speakers": 1378014, "language_name": "Susu", "autonym": "Susu", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nn", "speakers": 1366860, "language_name": "Norwegian Nynorsk", "autonym": "Norsk Nynorsk", "family": "Indo-European", "flores_path": "nno_Latn", "fleurs_tag": null, "commonvoice_hours": 1.5, "commonvoice_locale": "nn-NO", "in_benchmark": true }, { "bcp_47": "mgh", "speakers": 1354419, "language_name": "Makhuwa-Meetto", "autonym": "Makua", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "raj", "speakers": 1326090, "language_name": "Rajasthani", "autonym": "राजस्थानी", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hoc", "speakers": 1312829, "language_name": "Ho", "autonym": "Ho", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mdh", "speakers": 1310172, "language_name": "Maguindanaon", "autonym": "Maguindanaon", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mtr", "speakers": 1286307, "language_name": "Mewari", "autonym": "Mewari", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bum", "speakers": 1276270, "language_name": "Bulu", "autonym": "Bulu", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 9.7, "commonvoice_locale": "bum", "in_benchmark": false }, { "bcp_47": "myx", "speakers": 1254337, "language_name": "Masaaba", "autonym": "Masaaba", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "unr", "speakers": 1252287, "language_name": "Mundari", "autonym": "Mundari", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mfe", "speakers": 1241433, "language_name": "Morisyen", "autonym": "Kreol Morisien", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ga", "speakers": 1237487, "language_name": "Irish", "autonym": "Gaeilge", "family": "Indo-European", "flores_path": "gle_Latn", "fleurs_tag": "ga_ie", "commonvoice_hours": 6.2, "commonvoice_locale": "ga-IE", "in_benchmark": true }, { "bcp_47": "fvr", "speakers": 1230163, "language_name": "Fur", "autonym": "Fur", "family": "Furan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rej", "speakers": 1228320, "language_name": "Rejang", "autonym": "Rejang", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bhi", "speakers": 1220003, "language_name": "Bhilali", "autonym": "Bhilali", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tsg", "speakers": 1200991, "language_name": "Tausug", "autonym": "Tausug", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "quc", "speakers": 1200731, "language_name": "Kʼicheʼ", "autonym": "KʼIcheʼ", "family": "Mayan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "quc", "in_benchmark": false }, { "bcp_47": "bqi", "speakers": 1188926, "language_name": "Bakhtiari", "autonym": "Bakhtiari", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kpe", "speakers": 1186303, "language_name": "Kpelle", "autonym": "Kpɛlɛɛ", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sef", "speakers": 1181687, "language_name": "Cebaara Senoufo", "autonym": "Cebaara Senoufo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kxm", "speakers": 1172616, "language_name": "Northern Khmer", "autonym": "Northern Khmer", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "vls", "speakers": 1172070, "language_name": "West Flemish", "autonym": "West Flemish", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "snk", "speakers": 1153651, "language_name": "Soninke", "autonym": "Soninke", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "snk", "in_benchmark": false }, { "bcp_47": "zza", "speakers": 1148245, "language_name": "Zaza", "autonym": "Zaza", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 1.8, "commonvoice_locale": "zza", "in_benchmark": false }, { "bcp_47": "lv", "speakers": 1147550, "language_name": "Latvian", "autonym": "Latviešu", "family": "Indo-European", "flores_path": "lvs_Latn", "fleurs_tag": "lv_lv", "commonvoice_hours": 261.0, "commonvoice_locale": "lv", "in_benchmark": true }, { "bcp_47": "dnj", "speakers": 1099244, "language_name": "Dan", "autonym": "Dan", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gor", "speakers": 1094807, "language_name": "Gorontalo", "autonym": "Gorontalo", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tig", "speakers": 1094616, "language_name": "Tigre", "autonym": "Tigre", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 12.0, "commonvoice_locale": "tig", "in_benchmark": false }, { "bcp_47": "eu", "speakers": 1088519, "language_name": "Basque", "autonym": "Euskara", "family": null, "flores_path": "eus_Latn", "fleurs_tag": null, "commonvoice_hours": 337.0, "commonvoice_locale": "eu", "in_benchmark": true }, { "bcp_47": "hoj", "speakers": 1087394, "language_name": "Hadothi", "autonym": "Hadothi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kbd", "speakers": 1070873, "language_name": "Kabardian", "autonym": "Kabardian", "family": "Abkhaz-Adyge", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 45.0, "commonvoice_locale": "kbd", "in_benchmark": false }, { "bcp_47": "kha", "speakers": 1060872, "language_name": "Khasi", "autonym": "Khasi", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sc", "speakers": 1060846, "language_name": "Sardinian", "autonym": "Sardu", "family": "Indo-European", "flores_path": "srd_Latn", "fleurs_tag": null, "commonvoice_hours": 2.9, "commonvoice_locale": "sc", "in_benchmark": true }, { "bcp_47": "loz", "speakers": 1045596, "language_name": "Lozi", "autonym": "Lozi", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gur", "speakers": 1026907, "language_name": "Frafra", "autonym": "Frafra", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ars", "speakers": 1025205, "language_name": "Najdi Arabic", "autonym": "Najdi Arabic", "family": "Afro-Asiatic", "flores_path": "ars_Arab", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "rng", "speakers": 1023339, "language_name": "Ronga", "autonym": "Ronga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "luz", "speakers": 1019080, "language_name": "Southern Luri", "autonym": "Southern Luri", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "new", "speakers": 1000821, "language_name": "Newari", "autonym": "Newari", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "new", "in_benchmark": false }, { "bcp_47": "tly", "speakers": 1000168, "language_name": "Talysh", "autonym": "Talysh", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "yi", "speakers": 997214, "language_name": "Yiddish", "autonym": "ייִדיש", "family": "Indo-European", "flores_path": "ydd_Hebr", "fleurs_tag": null, "commonvoice_hours": 0.5, "commonvoice_locale": "yi", "in_benchmark": true }, { "bcp_47": "bez", "speakers": 995398, "language_name": "Bena", "autonym": "Hibena", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ksb", "speakers": 995398, "language_name": "Shambala", "autonym": "Kishambaa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kfr", "speakers": 994568, "language_name": "Kachhi", "autonym": "Kachhi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nij", "speakers": 987996, "language_name": "Ngaju", "autonym": "Ngaju", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mwk", "speakers": 977670, "language_name": "Kita Maninkakan", "autonym": "Kita Maninkakan", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "jml", "speakers": 970493, "language_name": "Jumli", "autonym": "Jumli", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ryu", "speakers": 966404, "language_name": "Central Okinawan", "autonym": "Central Okinawan", "family": "Japonic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mnw", "speakers": 966114, "language_name": "Mon", "autonym": "Mon", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "qug", "speakers": 963579, "language_name": "Chimborazo Highland Quichua", "autonym": "Chimborazo Highland Quichua", "family": "Quechuan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "qug", "in_benchmark": false }, { "bcp_47": "kac", "speakers": 962032, "language_name": "Kachin", "autonym": "Kachin", "family": "Sino-Tibetan", "flores_path": "kac_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "hnd", "speakers": 957354, "language_name": "Southern Hindko", "autonym": "Southern Hindko", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "li", "speakers": 950422, "language_name": "Limburgish", "autonym": "Limburgish", "family": "Indo-European", "flores_path": "lim_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "mxc", "speakers": 945510, "language_name": "Manyika", "autonym": "Manyika", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ce", "speakers": 935365, "language_name": "Chechen", "autonym": "Нохчийн", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kj", "speakers": 920524, "language_name": "Kuanyama", "autonym": "Kuanyama", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nr", "speakers": 903418, "language_name": "South Ndebele", "autonym": "South Ndebele", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "nr", "in_benchmark": false }, { "bcp_47": "cy", "speakers": 884910, "language_name": "Welsh", "autonym": "Cymraeg", "family": "Indo-European", "flores_path": "cym_Latn", "fleurs_tag": "cy_gb", "commonvoice_hours": 124.0, "commonvoice_locale": "cy", "in_benchmark": true }, { "bcp_47": "ada", "speakers": 880206, "language_name": "Adangme", "autonym": "Adangme", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "et", "speakers": 878449, "language_name": "Estonian", "autonym": "Eesti", "family": "Uralic", "flores_path": "ekk_Latn", "fleurs_tag": "et_ee", "commonvoice_hours": 58.0, "commonvoice_locale": "et", "in_benchmark": true }, { "bcp_47": "prd", "speakers": 864342, "language_name": "Parsi-Dari", "autonym": "Parsi-Dari", "family": "Bookkeeping", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "yua", "speakers": 861955, "language_name": "Yucateco", "autonym": "Yucateco", "family": "Mayan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ewo", "speakers": 860095, "language_name": "Ewondo", "autonym": "Ewondo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 19.0, "commonvoice_locale": "ewo", "in_benchmark": false }, { "bcp_47": "kge", "speakers": 854483, "language_name": "Komering", "autonym": "Komering", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ttj", "speakers": 821807, "language_name": "Tooro", "autonym": "Tooro", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ttj", "in_benchmark": false }, { "bcp_47": "grt", "speakers": 821563, "language_name": "Garo", "autonym": "Garo", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gaa", "speakers": 821526, "language_name": "Ga", "autonym": "Gã", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mgy", "speakers": 819739, "language_name": "Mbunga", "autonym": "Mbunga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tet", "speakers": 816395, "language_name": "Tetum", "autonym": "Tetum", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "iba", "speakers": 816302, "language_name": "Iban", "autonym": "Iban", "family": "Bookkeeping", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "iba", "in_benchmark": false }, { "bcp_47": "ebu", "speakers": 802918, "language_name": "Embu", "autonym": "Kĩembu", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "swg", "speakers": 801597, "language_name": "Swabian", "autonym": "Swabian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hnj", "speakers": 781687, "language_name": "Hmong Njua", "autonym": "𞄀𞄄𞄰𞄩𞄍𞄜𞄰", "family": "Hmong-Mien", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kck", "speakers": 770954, "language_name": "Kalanga", "autonym": "Kalanga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dty", "speakers": 758198, "language_name": "Dotyali", "autonym": "Dotyali", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pcd", "speakers": 746330, "language_name": "Picard", "autonym": "Picard", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fy", "speakers": 743057, "language_name": "Western Frisian", "autonym": "Frysk", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 66.0, "commonvoice_locale": "fy-NL", "in_benchmark": false }, { "bcp_47": "ccp", "speakers": 729137, "language_name": "Chakma", "autonym": "𑄌𑄋𑄴𑄟𑄳𑄦", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "yao", "speakers": 722357, "language_name": "Yao", "autonym": "Yao", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "aoz", "speakers": 720970, "language_name": "Uab Meto", "autonym": "Uab Meto", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cps", "speakers": 720595, "language_name": "Capiznon", "autonym": "Capiznon", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "asa", "speakers": 702634, "language_name": "Asu", "autonym": "Kipare", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "blt", "speakers": 681177, "language_name": "Tai Dam", "autonym": "ꪼꪕꪒꪾ", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wa", "speakers": 679801, "language_name": "Walloon", "autonym": "Walon", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ses", "speakers": 664816, "language_name": "Koyraboro Senni", "autonym": "Koyraboro Senni", "family": "Songhay", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bfy", "speakers": 654424, "language_name": "Bagheli", "autonym": "Bagheli", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ast", "speakers": 650205, "language_name": "Asturian", "autonym": "Asturianu", "family": "Indo-European", "flores_path": "ast_Latn", "fleurs_tag": "ast_es", "commonvoice_hours": 0.8, "commonvoice_locale": "ast", "in_benchmark": true }, { "bcp_47": "lki", "speakers": 645417, "language_name": "Laki", "autonym": "Laki", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "unx", "speakers": 636523, "language_name": "Munda", "autonym": "Munda", "family": "Bookkeeping", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lis", "speakers": 627309, "language_name": "Lisu", "autonym": "Lisu", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nqo", "speakers": 626370, "language_name": "N’Ko", "autonym": "ߒߞߏ", "family": "Artificial Language", "flores_path": "nqo_Nkoo", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "nqo", "in_benchmark": true }, { "bcp_47": "gos", "speakers": 622094, "language_name": "Gronings", "autonym": "Gronings", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "gos", "in_benchmark": false }, { "bcp_47": "lol", "speakers": 620858, "language_name": "Mongo", "autonym": "Mongo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "thl", "speakers": 606558, "language_name": "Dangaura Tharu", "autonym": "Dangaura Tharu", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nap", "speakers": 605306, "language_name": "Neapolitan", "autonym": "Neapolitan", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nus", "speakers": 591427, "language_name": "Nuer", "autonym": "Thok Nath", "family": "Nilotic", "flores_path": "nus_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "br", "speakers": 563140, "language_name": "Breton", "autonym": "Brezhoneg", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 29.0, "commonvoice_locale": "br", "in_benchmark": false }, { "bcp_47": "pis", "speakers": 561780, "language_name": "Pijin", "autonym": "Pijin", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rcf", "speakers": 559185, "language_name": "Réunion Creole French", "autonym": "Réunion Creole French", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "av", "speakers": 552716, "language_name": "Avaric", "autonym": "Avaric", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ng", "speakers": 552315, "language_name": "Ndonga", "autonym": "Ndonga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "os", "speakers": 541444, "language_name": "Ossetic", "autonym": "Ирон", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.9, "commonvoice_locale": "os", "in_benchmark": false }, { "bcp_47": "udm", "speakers": 538544, "language_name": "Udmurt", "autonym": "Udmurt", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "udm", "in_benchmark": false }, { "bcp_47": "lij", "speakers": 536663, "language_name": "Ligurian", "autonym": "Ligure", "family": "Indo-European", "flores_path": "lij_Latn", "fleurs_tag": null, "commonvoice_hours": 5.1, "commonvoice_locale": "lij", "in_benchmark": true }, { "bcp_47": "kea", "speakers": 530762, "language_name": "Kabuverdianu", "autonym": "Kabuverdianu", "family": "Indo-European", "flores_path": "kea_Latn", "fleurs_tag": "kea_cv", "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "rue", "speakers": 527075, "language_name": "Rusyn", "autonym": "Rusyn", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "chm", "speakers": 524371, "language_name": "Mari", "autonym": "Mari", "family": "Uralic", "flores_path": "mhr_Cyrl", "fleurs_tag": null, "commonvoice_hours": 282.0, "commonvoice_locale": "mhr", "in_benchmark": true }, { "bcp_47": "scn", "speakers": 511702, "language_name": "Sicilian", "autonym": "Sicilianu", "family": "Indo-European", "flores_path": "scn_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "scn", "in_benchmark": true }, { "bcp_47": "lag", "speakers": 509409, "language_name": "Langi", "autonym": "Kɨlaangi", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bft", "speakers": 502520, "language_name": "Balti", "autonym": "Balti", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 18.0, "commonvoice_locale": "bft", "in_benchmark": false }, { "bcp_47": "nhe", "speakers": 501735, "language_name": "Eastern Huasteca Nahuatl", "autonym": "Eastern Huasteca Nahuatl", "family": "Uto-Aztecan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "nhe", "in_benchmark": false }, { "bcp_47": "nhw", "speakers": 501735, "language_name": "Western Huasteca Nahuatl", "autonym": "Western Huasteca Nahuatl", "family": "Uto-Aztecan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "szl", "speakers": 497670, "language_name": "Silesian", "autonym": "Ślōnski", "family": "Indo-European", "flores_path": "szl_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "kaa", "speakers": 489046, "language_name": "Kara-Kalpak", "autonym": "Kara-Kalpak", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "kaa", "in_benchmark": false }, { "bcp_47": "gju", "speakers": 467002, "language_name": "Gujari", "autonym": "Gujari", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "gju", "in_benchmark": false }, { "bcp_47": "srx", "speakers": 464132, "language_name": "Sirmauri", "autonym": "Sirmauri", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mt", "speakers": 457267, "language_name": "Maltese", "autonym": "Malti", "family": "Afro-Asiatic", "flores_path": "mlt_Latn", "fleurs_tag": "mt_mt", "commonvoice_hours": 8.7, "commonvoice_locale": "mt", "in_benchmark": true }, { "bcp_47": "bap", "speakers": 454918, "language_name": "Bantawa", "autonym": "Bantawa", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sah", "speakers": 453510, "language_name": "Yakut", "autonym": "Саха Тыла", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 14.0, "commonvoice_locale": "sah", "in_benchmark": false }, { "bcp_47": "mls", "speakers": 451060, "language_name": "Masalit", "autonym": "Masalit", "family": "Maban", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kaj", "speakers": 449459, "language_name": "Jju", "autonym": "Kaje", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ady", "speakers": 444583, "language_name": "Adyghe", "autonym": "Adyghe", "family": "Abkhaz-Adyge", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 13.0, "commonvoice_locale": "ady", "in_benchmark": false }, { "bcp_47": "ybb", "speakers": 443920, "language_name": "Yemba", "autonym": "Yemba", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "xmf", "speakers": 439670, "language_name": "Mingrelian", "autonym": "Mingrelian", "family": "Kartvelian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "xmf", "in_benchmark": false }, { "bcp_47": "myv", "speakers": 439338, "language_name": "Erzya", "autonym": "Эрзянь Кель", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 3.8, "commonvoice_locale": "myv", "in_benchmark": false }, { "bcp_47": "dav", "speakers": 438929, "language_name": "Taita", "autonym": "Kitaita", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 9.3, "commonvoice_locale": "dav", "in_benchmark": false }, { "bcp_47": "maz", "speakers": 437410, "language_name": "Central Mazahua", "autonym": "Central Mazahua", "family": "Otomanguean", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "vun", "speakers": 433291, "language_name": "Vunjo", "autonym": "Kyivunjo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rof", "speakers": 433291, "language_name": "Rombo", "autonym": "Kihorombo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "rof", "in_benchmark": false }, { "bcp_47": "jmc", "speakers": 433291, "language_name": "Machame", "autonym": "Kimachame", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kjg", "speakers": 431949, "language_name": "Khmu", "autonym": "Khmu", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fan", "speakers": 426451, "language_name": "Fang", "autonym": "Fang", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 9.3, "commonvoice_locale": "fan", "in_benchmark": false }, { "bcp_47": "krj", "speakers": 425806, "language_name": "Kinaray-a", "autonym": "Kinaray-A", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kdt", "speakers": 421207, "language_name": "Kuy", "autonym": "Kuy", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lb", "speakers": 421015, "language_name": "Luxembourgish", "autonym": "Lëtzebuergesch", "family": "Indo-European", "flores_path": "ltz_Latn", "fleurs_tag": "lb_lu", "commonvoice_hours": 0.0, "commonvoice_locale": "lb", "in_benchmark": true }, { "bcp_47": "srn", "speakers": 414507, "language_name": "Sranan Tongo", "autonym": "Sranan Tongo", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dyo", "speakers": 409146, "language_name": "Jola-Fonyi", "autonym": "Joola", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tdg", "speakers": 394263, "language_name": "Western Tamang", "autonym": "Western Tamang", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pnt", "speakers": 392463, "language_name": "Pontic", "autonym": "Pontic", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "zmi", "speakers": 391825, "language_name": "Negeri Sembilan Malay", "autonym": "Negeri Sembilan Malay", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nnh", "speakers": 388430, "language_name": "Ngiemboon", "autonym": "Shwóŋò Ngiembɔɔn", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 23.0, "commonvoice_locale": "nnh", "in_benchmark": false }, { "bcp_47": "bbj", "speakers": 388430, "language_name": "Ghomala", "autonym": "Ghomala", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 13.0, "commonvoice_locale": "bbj", "in_benchmark": false }, { "bcp_47": "dv", "speakers": 388044, "language_name": "Divehi", "autonym": "Divehi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 39.0, "commonvoice_locale": "dv", "in_benchmark": false }, { "bcp_47": "saz", "speakers": 384566, "language_name": "Saurashtra", "autonym": "Saurashtra", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hif", "speakers": 383749, "language_name": "Fiji Hindi", "autonym": "Fiji Hindi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fia", "speakers": 378161, "language_name": "Nobiin", "autonym": "Nobiin", "family": "Nubian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bgx", "speakers": 377280, "language_name": "Balkan Gagauz Turkish", "autonym": "Balkan Gagauz Turkish", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kvr", "speakers": 373836, "language_name": "Kerinci", "autonym": "Kerinci", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kvx", "speakers": 373602, "language_name": "Parkari Koli", "autonym": "Parkari Koli", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 5.8, "commonvoice_locale": "kvx", "in_benchmark": false }, { "bcp_47": "dz", "speakers": 370341, "language_name": "Dzongkha", "autonym": "རྫོང་ཁ", "family": "Bookkeeping", "flores_path": "dzo_Tibt", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "pko", "speakers": 369343, "language_name": "Pökoot", "autonym": "Pökoot", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dar", "speakers": 368477, "language_name": "Dargwa", "autonym": "Dargwa", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "dar", "in_benchmark": false }, { "bcp_47": "lif", "speakers": 368085, "language_name": "Limbu", "autonym": "Limbu", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fj", "speakers": 365030, "language_name": "Fijian", "autonym": "Fijian", "family": "Austronesian", "flores_path": "fij_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "thr", "speakers": 363935, "language_name": "Rana Tharu", "autonym": "Rana Tharu", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bkm", "speakers": 360685, "language_name": "Kom", "autonym": "Kom", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 13.0, "commonvoice_locale": "bkm", "in_benchmark": false }, { "bcp_47": "is", "speakers": 350734, "language_name": "Icelandic", "autonym": "Íslenska", "family": "Indo-European", "flores_path": "isl_Latn", "fleurs_tag": "is_is", "commonvoice_hours": 0.1, "commonvoice_locale": "is", "in_benchmark": true }, { "bcp_47": "khw", "speakers": 350252, "language_name": "Khowar", "autonym": "Khowar", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 18.0, "commonvoice_locale": "khw", "in_benchmark": false }, { "bcp_47": "lbw", "speakers": 347134, "language_name": "Tolaki", "autonym": "Tolaki", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nxq", "speakers": 334565, "language_name": "Naxi", "autonym": "Naxi", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mgp", "speakers": 333607, "language_name": "Eastern Magar", "autonym": "Eastern Magar", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bax", "speakers": 332940, "language_name": "Bamun", "autonym": "Bamun", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "bax", "in_benchmark": false }, { "bcp_47": "bas", "speakers": 332940, "language_name": "Basaa", "autonym": "Ɓàsàa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 12.0, "commonvoice_locale": "bas", "in_benchmark": false }, { "bcp_47": "khq", "speakers": 332408, "language_name": "Koyra Chiini", "autonym": "Koyra Ciini", "family": "Songhay", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mvy", "speakers": 326901, "language_name": "Indus Kohistani", "autonym": "Indus Kohistani", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 23.0, "commonvoice_locale": "mvy", "in_benchmark": false }, { "bcp_47": "gay", "speakers": 320431, "language_name": "Gayo", "autonym": "Gayo", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "zdj", "speakers": 313124, "language_name": "Ngazidja Comorian", "autonym": "Ngazidja Comorian", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bua", "speakers": 311788, "language_name": "Buriat", "autonym": "Buriat", "family": "Mongolic-Khitan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "bxr", "in_benchmark": false }, { "bcp_47": "bto", "speakers": 305707, "language_name": "Rinconada Bikol", "autonym": "Rinconada Bikol", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "byv", "speakers": 305195, "language_name": "Medumba", "autonym": "Medumba", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 14.0, "commonvoice_locale": "byv", "in_benchmark": false }, { "bcp_47": "njo", "speakers": 305001, "language_name": "Ao Naga", "autonym": "Ao Naga", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bfq", "speakers": 305001, "language_name": "Badaga", "autonym": "Badaga", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "thq", "speakers": 303279, "language_name": "Kochila Tharu", "autonym": "Kochila Tharu", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mdf", "speakers": 297616, "language_name": "Moksha", "autonym": "Мокшень Кяль", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.5, "commonvoice_locale": "mdf", "in_benchmark": false }, { "bcp_47": "rob", "speakers": 293729, "language_name": "Tae'", "autonym": "Tae'", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nzi", "speakers": 293402, "language_name": "Nzima", "autonym": "Nzima", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "naq", "speakers": 289308, "language_name": "Nama", "autonym": "Khoekhoegowab", "family": "Khoe-Kwadi", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wni", "speakers": 287736, "language_name": "Ndzwani Comorian", "autonym": "Ndzwani Comorian", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kum", "speakers": 283444, "language_name": "Kumyk", "autonym": "Kumyk", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mua", "speakers": 277450, "language_name": "Mundang", "autonym": "Mundaŋ", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "mua", "in_benchmark": false }, { "bcp_47": "arn", "speakers": 272802, "language_name": "Mapuche", "autonym": "Mapudungun", "family": "Araucanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "arn", "in_benchmark": false }, { "bcp_47": "cja", "speakers": 270832, "language_name": "Western Cham", "autonym": "Western Cham", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bi", "speakers": 268500, "language_name": "Bislama", "autonym": "Bislama", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "khb", "speakers": 264864, "language_name": "Lü", "autonym": "Lü", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tdd", "speakers": 264864, "language_name": "Tai Nüa", "autonym": "Tai Nüa", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kxp", "speakers": 256851, "language_name": "Wadiyara Koli", "autonym": "Wadiyara Koli", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 4.1, "commonvoice_locale": "kxp", "in_benchmark": false }, { "bcp_47": "gjk", "speakers": 256851, "language_name": "Kachi Koli", "autonym": "Kachi Koli", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "gjk", "in_benchmark": false }, { "bcp_47": "lez", "speakers": 255100, "language_name": "Lezghian", "autonym": "Lezghian", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kv", "speakers": 255100, "language_name": "Komi", "autonym": "Komi", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "kpv", "in_benchmark": false }, { "bcp_47": "sm", "speakers": 252717, "language_name": "Samoan", "autonym": "Samoan", "family": "Austronesian", "flores_path": "smo_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "mrd", "speakers": 251722, "language_name": "Western Magar", "autonym": "Western Magar", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "saq", "speakers": 246228, "language_name": "Samburu", "autonym": "Kisampur", "family": "Nilotic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "crh", "speakers": 245968, "language_name": "Crimean Tatar", "autonym": "Crimean Tatar", "family": "Turkic", "flores_path": "crh_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "crh", "in_benchmark": true }, { "bcp_47": "mdr", "speakers": 245664, "language_name": "Mandar", "autonym": "Mandar", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sxn", "speakers": 245664, "language_name": "Sangir", "autonym": "Sangir", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ext", "speakers": 245077, "language_name": "Extremaduran", "autonym": "Extremaduran", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nch", "speakers": 244435, "language_name": "Central Huasteca Nahuatl", "autonym": "Central Huasteca Nahuatl", "family": "Uto-Aztecan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "zea", "speakers": 241926, "language_name": "Zeelandic", "autonym": "Zeelandic", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "krc", "speakers": 240927, "language_name": "Karachay-Balkar", "autonym": "Karachay-Balkar", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "krc", "in_benchmark": false }, { "bcp_47": "ksh", "speakers": 240479, "language_name": "Colognian", "autonym": "Kölsch", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hz", "speakers": 239336, "language_name": "Herero", "autonym": "Herero", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sav", "speakers": 236046, "language_name": "Saafi-Saafi", "autonym": "Saafi-Saafi", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "zag", "speakers": 232364, "language_name": "Zaghawa", "autonym": "Zaghawa", "family": "Saharan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "inh", "speakers": 226755, "language_name": "Ingush", "autonym": "Ingush", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ssy", "speakers": 218923, "language_name": "Saho", "autonym": "Saho", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dtm", "speakers": 215087, "language_name": "Tomo Kan Dogon", "autonym": "Tomo Kan Dogon", "family": "Dogon", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pap", "speakers": 211640, "language_name": "Papiamento", "autonym": "Papiamentu", "family": "Indo-European", "flores_path": "pap_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "pap-AW", "in_benchmark": true }, { "bcp_47": "syr", "speakers": 210659, "language_name": "Syriac", "autonym": "ܣܘܪܝܝܐ", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "syr", "in_benchmark": false }, { "bcp_47": "tog", "speakers": 207727, "language_name": "Nyasa Tonga", "autonym": "Nyasa Tonga", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "maf", "speakers": 205313, "language_name": "Mafa", "autonym": "Mafa", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "puu", "speakers": 200782, "language_name": "Punu", "autonym": "Punu", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kcg", "speakers": 199046, "language_name": "Tyap", "autonym": "Katab", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kao", "speakers": 195534, "language_name": "Xaasongaxango", "autonym": "Xaasongaxango", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tyv", "speakers": 184239, "language_name": "Tuvinian", "autonym": "Tuvinian", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "tyv", "in_benchmark": false }, { "bcp_47": "dtp", "speakers": 182852, "language_name": "Central Dusun", "autonym": "Central Dusun", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ria", "speakers": 172392, "language_name": "Riang (India)", "autonym": "Riang (India)", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "swb", "speakers": 170720, "language_name": "Comorian", "autonym": "Comorian", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bmq", "speakers": 168159, "language_name": "Bomu", "autonym": "Bomu", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ltg", "speakers": 167429, "language_name": "Latgalian", "autonym": "Latgalian", "family": "Indo-European", "flores_path": "ltg_Latn", "fleurs_tag": null, "commonvoice_hours": 29.0, "commonvoice_locale": "ltg", "in_benchmark": true }, { "bcp_47": "nv", "speakers": 166320, "language_name": "Navajo", "autonym": "Diné Bizaad", "family": "Athabaskan-Eyak-Tlingit", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bze", "speakers": 166204, "language_name": "Jenaama Bozo", "autonym": "Jenaama Bozo", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "co", "speakers": 162836, "language_name": "Corsican", "autonym": "Corsu", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "co", "in_benchmark": false }, { "bcp_47": "bfd", "speakers": 158146, "language_name": "Bafut", "autonym": "Bafut", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "bfd", "in_benchmark": false }, { "bcp_47": "xsr", "speakers": 157705, "language_name": "Sherpa", "autonym": "Sherpa", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kiu", "speakers": 155833, "language_name": "Kirmanjki", "autonym": "Kirmanjki", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ho", "speakers": 152449, "language_name": "Hiri Motu", "autonym": "Hiri Motu", "family": "Pidgin", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kkj", "speakers": 149823, "language_name": "Kako", "autonym": "Kakɔ", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bss", "speakers": 149823, "language_name": "Akoose", "autonym": "Akoose", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sly", "speakers": 144194, "language_name": "Selayar", "autonym": "Selayar", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mi", "speakers": 137913, "language_name": "Māori", "autonym": "Māori", "family": "Austronesian", "flores_path": "mri_Latn", "fleurs_tag": "mi_nz", "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "rjs", "speakers": 133443, "language_name": "Rajbanshi", "autonym": "Rajbanshi", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dua", "speakers": 133176, "language_name": "Duala", "autonym": "Duálá", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 14.0, "commonvoice_locale": "dua", "in_benchmark": false }, { "bcp_47": "guc", "speakers": 132529, "language_name": "Wayuu", "autonym": "Wayuu", "family": "Arawakan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "guc", "in_benchmark": false }, { "bcp_47": "vai", "speakers": 131906, "language_name": "Vai", "autonym": "ꕙꔤ", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "taj", "speakers": 130410, "language_name": "Eastern Tamang", "autonym": "Eastern Tamang", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mgo", "speakers": 130401, "language_name": "Metaʼ", "autonym": "Metaʼ", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pdc", "speakers": 129729, "language_name": "Pennsylvania German", "autonym": "Pennsylvania German", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rwk", "speakers": 128816, "language_name": "Rwa", "autonym": "Kiruwa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "trw", "speakers": 123756, "language_name": "Torwali", "autonym": "توروالی", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 19.0, "commonvoice_locale": "trw", "in_benchmark": false }, { "bcp_47": "mfv", "speakers": 121170, "language_name": "Mandjak", "autonym": "Mandjak", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tsj", "speakers": 117348, "language_name": "Tshangla", "autonym": "Tshangla", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sbp", "speakers": 117106, "language_name": "Sangu", "autonym": "Ishisangu", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "krl", "speakers": 116212, "language_name": "Karelian", "autonym": "Karelian", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lad", "speakers": 112781, "language_name": "Ladino", "autonym": "Ladino", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ife", "speakers": 111910, "language_name": "Ifè", "autonym": "Ifè", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gag", "speakers": 111028, "language_name": "Gagauz", "autonym": "Gagauz", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lbe", "speakers": 110543, "language_name": "Lak", "autonym": "Lak", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sdc", "speakers": 106085, "language_name": "Sassarese Sardinian", "autonym": "Sassarese Sardinian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "to", "speakers": 100790, "language_name": "Tongan", "autonym": "Lea Fakatonga", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bjt", "speakers": 95992, "language_name": "Balanta-Ganja", "autonym": "Balanta-Ganja", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "jgo", "speakers": 94333, "language_name": "Ngomba", "autonym": "Ndaꞌa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "jgo", "in_benchmark": false }, { "bcp_47": "crs", "speakers": 94061, "language_name": "Seselwa Creole French", "autonym": "Seselwa Creole French", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ab", "speakers": 91953, "language_name": "Abkhazian", "autonym": "Аԥсшәа", "family": "Abkhaz-Adyge", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 68.0, "commonvoice_locale": "ab", "in_benchmark": false }, { "bcp_47": "ty", "speakers": 91488, "language_name": "Tahitian", "autonym": "Tahitian", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ty", "in_benchmark": false }, { "bcp_47": "iu", "speakers": 90466, "language_name": "Inuktitut", "autonym": "Inuktitut", "family": "Eskimo-Aleut", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pdt", "speakers": 90466, "language_name": "Plautdietsch", "autonym": "Plautdietsch", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bpy", "speakers": 90174, "language_name": "Bishnupriya", "autonym": "Bishnupriya", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ksf", "speakers": 88784, "language_name": "Bafia", "autonym": "Rikpa", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 20.0, "commonvoice_locale": "ksf", "in_benchmark": false }, { "bcp_47": "gvr", "speakers": 87951, "language_name": "Gurung", "autonym": "Gurung", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cjm", "speakers": 87862, "language_name": "Eastern Cham", "autonym": "Eastern Cham", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lcp", "speakers": 87751, "language_name": "Western Lawa", "autonym": "Western Lawa", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "knf", "speakers": 83151, "language_name": "Mankanya", "autonym": "Mankanya", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lep", "speakers": 79743, "language_name": "Lepcha", "autonym": "Lepcha", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "byn", "speakers": 79056, "language_name": "Blin", "autonym": "Blin", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "btv", "speakers": 78843, "language_name": "Bateri", "autonym": "Bateri", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "btv", "in_benchmark": false }, { "bcp_47": "tkt", "speakers": 72787, "language_name": "Kathoriya Tharu", "autonym": "Kathoriya Tharu", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gd", "speakers": 72337, "language_name": "Scottish Gaelic", "autonym": "Gàidhlig", "family": "Indo-European", "flores_path": "gla_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "fo", "speakers": 71351, "language_name": "Faroese", "autonym": "Føroyskt", "family": "Indo-European", "flores_path": "fao_Latn", "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "fo", "in_benchmark": true }, { "bcp_47": "vro", "speakers": 70031, "language_name": "Võro", "autonym": "Võro", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ken", "speakers": 69362, "language_name": "Kenyang", "autonym": "Kɛnyaŋ", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gil", "speakers": 67078, "language_name": "Gilbertese", "autonym": "Gilbertese", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bvb", "speakers": 66058, "language_name": "Bube", "autonym": "Bube", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mwv", "speakers": 64086, "language_name": "Mentawai", "autonym": "Mentawai", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "frp", "speakers": 63777, "language_name": "Arpitan", "autonym": "Arpitan", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "koi", "speakers": 63775, "language_name": "Komi-Permyak", "autonym": "Komi-Permyak", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kfo", "speakers": 63207, "language_name": "Koro", "autonym": "Koro", "family": "Mande", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mh", "speakers": 56879, "language_name": "Marshallese", "autonym": "Marshallese", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fit", "speakers": 56114, "language_name": "Tornedalen Finnish", "autonym": "Tornedalen Finnish", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kl", "speakers": 55440, "language_name": "Kalaallisut", "autonym": "Kalaallisut", "family": "Eskimo-Aleut", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bra", "speakers": 54370, "language_name": "Braj", "autonym": "Braj", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gcr", "speakers": 51872, "language_name": "Guianese Creole French", "autonym": "Guianese Creole French", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "se", "speakers": 51530, "language_name": "Northern Sami", "autonym": "Davvisámegiella", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "blo", "speakers": 51507, "language_name": "Anii", "autonym": "Anii Kagɩja", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kgp", "speakers": 50812, "language_name": "Kaingang", "autonym": "Kanhgág", "family": "Nuclear-Macro-Je", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "csb", "speakers": 49767, "language_name": "Kashubian", "autonym": "Kashubian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bqv", "speakers": 46718, "language_name": "Koro Wachi", "autonym": "Koro Wachi", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ch", "speakers": 46325, "language_name": "Chamorro", "autonym": "Chamorro", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cch", "speakers": 44946, "language_name": "Atsam", "autonym": "Atsam", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "buc", "speakers": 44620, "language_name": "Bushi", "autonym": "Bushi", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rm", "speakers": 42020, "language_name": "Romansh", "autonym": "Rumantsch", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "agq", "speakers": 38843, "language_name": "Aghem", "autonym": "Aghem", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kxv", "speakers": 38457, "language_name": "Kuvi", "autonym": "Kuvi", "family": "Dravidian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "snf", "speakers": 37767, "language_name": "Noon", "autonym": "Noon", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fur", "speakers": 37442, "language_name": "Friulian", "autonym": "Furlan", "family": "Indo-European", "flores_path": "fur_Latn", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "tdh", "speakers": 36393, "language_name": "Thulung", "autonym": "Thulung", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "egl", "speakers": 31201, "language_name": "Emilian", "autonym": "Emilian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "chk", "speakers": 30731, "language_name": "Chuukese", "autonym": "Chuukese", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mrj", "speakers": 29762, "language_name": "Western Mari", "autonym": "Western Mari", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 34.0, "commonvoice_locale": "mrj", "in_benchmark": false }, { "bcp_47": "haw", "speakers": 29605, "language_name": "Hawaiian", "autonym": "ʻŌlelo HawaiʻI", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mro", "speakers": 29277, "language_name": "Mru", "autonym": "Mru", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "frc", "speakers": 27942, "language_name": "Cajun French", "autonym": "Cajun French", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "yrl", "speakers": 26171, "language_name": "Nheengatu", "autonym": "Nheẽgatu", "family": "Tupian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "an", "speakers": 26008, "language_name": "Aragonese", "autonym": "Aragonés", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 17.0, "commonvoice_locale": "an", "in_benchmark": false }, { "bcp_47": "chr", "speakers": 25613, "language_name": "Cherokee", "autonym": "Ꮳꮃꭹ", "family": "Iroquoian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rmo", "speakers": 24372, "language_name": "Sinte Romani", "autonym": "Sinte Romani", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "oj", "speakers": 23747, "language_name": "Ojibwa", "autonym": "Ojibwa", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pon", "speakers": 23560, "language_name": "Pohnpeian", "autonym": "Pohnpeian", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lzz", "speakers": 22965, "language_name": "Laz", "autonym": "Laz", "family": "Kartvelian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "lzz", "in_benchmark": false }, { "bcp_47": "ttt", "speakers": 22453, "language_name": "Muslim Tat", "autonym": "Muslim Tat", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "esu", "speakers": 20956, "language_name": "Central Yupik", "autonym": "Central Yupik", "family": "Eskimo-Aleut", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 7.6, "commonvoice_locale": "esu", "in_benchmark": false }, { "bcp_47": "dak", "speakers": 20832, "language_name": "Dakota", "autonym": "Dakota", "family": "Siouan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "alt", "speakers": 19841, "language_name": "Southern Altai", "autonym": "Southern Altai", "family": "Turkic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "amo", "speakers": 18620, "language_name": "Amo", "autonym": "Amo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gub", "speakers": 17784, "language_name": "Guajajára", "autonym": "Guajajára", "family": "Tupian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hnn", "speakers": 17469, "language_name": "Hanunoo", "autonym": "Hanunoo", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tkr", "speakers": 16329, "language_name": "Tsakhur", "autonym": "Tsakhur", "family": "Nakh-Daghestanian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pau", "speakers": 16047, "language_name": "Palauan", "autonym": "Palauan", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sa", "speakers": 15913, "language_name": "Sanskrit", "autonym": "संस्कृत भाषा", "family": "Indo-European", "flores_path": "san_Deva", "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": true }, { "bcp_47": "bsc", "speakers": 15264, "language_name": "Bassari", "autonym": "Bassari", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ojs", "speakers": 15078, "language_name": "Oji-Cree", "autonym": "Oji-Cree", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kht", "speakers": 13527, "language_name": "Khamti", "autonym": "Khamti", "family": "Tai-Kadai", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hsb", "speakers": 12826, "language_name": "Upper Sorbian", "autonym": "Hornjoserbšćina", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 2.9, "commonvoice_locale": "hsb", "in_benchmark": false }, { "bcp_47": "chp", "speakers": 12816, "language_name": "Chipewyan", "autonym": "Chipewyan", "family": "Athabaskan-Eyak-Tlingit", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "moe", "speakers": 12062, "language_name": "Innu-aimun", "autonym": "Innu-Aimun", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sli", "speakers": 11868, "language_name": "Lower Silesian", "autonym": "Lower Silesian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wae", "speakers": 11377, "language_name": "Walser", "autonym": "Walser", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cho", "speakers": 10977, "language_name": "Choctaw", "autonym": "Chahta", "family": "Muskogean", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tbw", "speakers": 10045, "language_name": "Tagbanwa", "autonym": "Tagbanwa", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "xav", "speakers": 9951, "language_name": "Xavánte", "autonym": "Xavánte", "family": "Nuclear-Macro-Je", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tvl", "speakers": 9868, "language_name": "Tuvalu", "autonym": "Tuvalu", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "frr", "speakers": 9619, "language_name": "Northern Frisian", "autonym": "Nordfriisk", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rug", "speakers": 9591, "language_name": "Roviana", "autonym": "Roviana", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wls", "speakers": 9512, "language_name": "Wallisian", "autonym": "Wallisian", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rmu", "speakers": 9488, "language_name": "Tavringer Romani", "autonym": "Tavringer Romani", "family": "Speech Register", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cr", "speakers": 9047, "language_name": "Cree", "autonym": "Cree", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nmg", "speakers": 8878, "language_name": "Kwasio", "autonym": "Kwasio", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lkt", "speakers": 8316, "language_name": "Lakota", "autonym": "LakȟólʼIyapi", "family": "Siouan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kos", "speakers": 7990, "language_name": "Kosraean", "autonym": "Kosraean", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ik", "speakers": 7983, "language_name": "Inupiaq", "autonym": "Inupiaq", "family": "Eskimo-Aleut", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 7.2, "commonvoice_locale": "ipk", "in_benchmark": false }, { "bcp_47": "gbz", "speakers": 7983, "language_name": "Zoroastrian Dari", "autonym": "Zoroastrian Dari", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "twq", "speakers": 7970, "language_name": "Tasawaq", "autonym": "Tasawaq Senni", "family": "Songhay", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bku", "speakers": 7970, "language_name": "Buhid", "autonym": "Buhid", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mic", "speakers": 7916, "language_name": "Mi'kmaw", "autonym": "LʼNuiʼSuti", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mey", "speakers": 7239, "language_name": "Hassaniyya", "autonym": "Hassaniyya", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dsb", "speakers": 6974, "language_name": "Lower Sorbian", "autonym": "Dolnoserbšćina", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "dsb", "in_benchmark": false }, { "bcp_47": "na", "speakers": 6930, "language_name": "Nauru", "autonym": "Nauru", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lwl", "speakers": 6898, "language_name": "Eastern Lawa", "autonym": "Eastern Lawa", "family": "Austroasiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "yap", "speakers": 6556, "language_name": "Yapese", "autonym": "Yapese", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "atj", "speakers": 6408, "language_name": "Atikamekw", "autonym": "Atikamekw", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pms", "speakers": 6178, "language_name": "Piedmontese", "autonym": "Piedmontese", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rmf", "speakers": 5015, "language_name": "Kalo Finnish Romani", "autonym": "Kalo Finnish Romani", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "bla", "speakers": 4900, "language_name": "Siksiká", "autonym": "Siksiká", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "fud", "speakers": 4756, "language_name": "East Futuna", "autonym": "East Futuna", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "trv", "speakers": 4721, "language_name": "Taroko", "autonym": "Patas Taroko", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 10.0, "commonvoice_locale": "trv", "in_benchmark": false }, { "bcp_47": "crk", "speakers": 4146, "language_name": "Plains Cree", "autonym": "Plains Cree", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "saf", "speakers": 4108, "language_name": "Safaliba", "autonym": "Safaliba", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "mus", "speakers": 3992, "language_name": "Muscogee", "autonym": "Mvskoke", "family": "Muskogean", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "vep", "speakers": 3543, "language_name": "Veps", "autonym": "Veps", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tnr", "speakers": 3305, "language_name": "Ménik", "autonym": "Ménik", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "vic", "speakers": 3113, "language_name": "Virgin Islands Creole English", "autonym": "Virgin Islands Creole English", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tru", "speakers": 3035, "language_name": "Turoyo", "autonym": "Turoyo", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "uli", "speakers": 2971, "language_name": "Ulithian", "autonym": "Ulithian", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rtm", "speakers": 2527, "language_name": "Rotuman", "autonym": "Rotuman", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "wbp", "speakers": 2496, "language_name": "Warlpiri", "autonym": "Warlpiri", "family": "Pama-Nyungan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "yav", "speakers": 2303, "language_name": "Yangben", "autonym": "Nuasue", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "yav", "in_benchmark": false }, { "bcp_47": "den", "speakers": 2299, "language_name": "Slave", "autonym": "Slave", "family": "Athabaskan-Eyak-Tlingit", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "dgr", "speakers": 2111, "language_name": "Dogrib", "autonym": "Dogrib", "family": "Athabaskan-Eyak-Tlingit", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "frs", "speakers": 2004, "language_name": "Eastern Frisian", "autonym": "Eastern Frisian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kw", "speakers": 1973, "language_name": "Cornish", "autonym": "Kernewek", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 13.0, "commonvoice_locale": "kw", "in_benchmark": false }, { "bcp_47": "csw", "speakers": 1809, "language_name": "Swampy Cree", "autonym": "ᓀᐦᐃᓇᐍᐏᐣ", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "moh", "speakers": 1772, "language_name": "Mohawk", "autonym": "KanienʼKéha", "family": "Iroquoian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gv", "speakers": 1719, "language_name": "Manx", "autonym": "Gaelg", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "gv", "in_benchmark": false }, { "bcp_47": "smj", "speakers": 1530, "language_name": "Lule Sami", "autonym": "Julevsámegiella", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "nsk", "speakers": 1395, "language_name": "Naskapi", "autonym": "Naskapi", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tkl", "speakers": 1285, "language_name": "Tokelau", "autonym": "Tokelau", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "niu", "speakers": 1120, "language_name": "Niuean", "autonym": "Niuean", "family": "Austronesian", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "stq", "speakers": 962, "language_name": "Saterland Frisian", "autonym": "Saterland Frisian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sei", "speakers": 901, "language_name": "Seri", "autonym": "Seri", "family": null, "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 11.0, "commonvoice_locale": "sei", "in_benchmark": false }, { "bcp_47": "clc", "speakers": 867, "language_name": "Chilcotin", "autonym": "Chilcotin", "family": "Athabaskan-Eyak-Tlingit", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "la", "speakers": 820, "language_name": "Latin", "autonym": "Lingua Latina", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "hur", "speakers": 716, "language_name": "Halkomelem", "autonym": "Halkomelem", "family": "Salishan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "crg", "speakers": 678, "language_name": "Michif", "autonym": "Michif", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sms", "speakers": 613, "language_name": "Skolt Sami", "autonym": "SääʹMǩiõll", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "smn", "speakers": 613, "language_name": "Inari Sami", "autonym": "Anarâškielâ", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "lil", "speakers": 528, "language_name": "Lillooet", "autonym": "Lillooet", "family": "Salishan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "oka", "speakers": 490, "language_name": "Okanagan", "autonym": "Okanagan", "family": "Salishan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pqm", "speakers": 490, "language_name": "Maliseet-Passamaquoddy", "autonym": "Maliseet-Passamaquoddy", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "kwk", "speakers": 377, "language_name": "Kwakʼwala", "autonym": "KwakʼWala", "family": "Wakashan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "crl", "speakers": 377, "language_name": "Northern East Cree", "autonym": "Northern East Cree", "family": "Algic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "gwi", "speakers": 302, "language_name": "Gwichʼin", "autonym": "GwichʼIn", "family": "Athabaskan-Eyak-Tlingit", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "eo", "speakers": 301, "language_name": "Esperanto", "autonym": "Esperanto", "family": "Artificial Language", "flores_path": "epo_Latn", "fleurs_tag": null, "commonvoice_hours": 1436.0, "commonvoice_locale": "eo", "in_benchmark": true }, { "bcp_47": "sma", "speakers": 296, "language_name": "Southern Sami", "autonym": "Åarjelsaemien Gïele", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "tsd", "speakers": 202, "language_name": "Tsakonian", "autonym": "Tsakonian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "izh", "speakers": 142, "language_name": "Ingrian", "autonym": "Ingrian", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "izh", "in_benchmark": false }, { "bcp_47": "ia", "speakers": 136, "language_name": "Interlingua", "autonym": "Interlingua", "family": "Artificial Language", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 15.0, "commonvoice_locale": "ia", "in_benchmark": false }, { "bcp_47": "aro", "speakers": 105, "language_name": "Araona", "autonym": "Araona", "family": "Pano-Tacanan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "prg", "speakers": 38, "language_name": "Prussian", "autonym": "Prūsiskan", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ie", "speakers": 1, "language_name": "Interlingue", "autonym": "Interlingue", "family": "Artificial Language", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "ie", "in_benchmark": false }, { "bcp_47": "lzh", "speakers": 0, "language_name": "Literary Chinese", "autonym": "Literary Chinese", "family": "Sino-Tibetan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "io", "speakers": 0, "language_name": "Ido", "autonym": "Ido", "family": "Artificial Language", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "jbo", "speakers": 0, "language_name": "Lojban", "autonym": "La .Lojban.", "family": "Artificial Language", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.0, "commonvoice_locale": "jbo", "in_benchmark": false }, { "bcp_47": "jut", "speakers": 0, "language_name": "Jutish", "autonym": "Jutish", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "vot", "speakers": 0, "language_name": "Votic", "autonym": "Votic", "family": "Uralic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": 0.1, "commonvoice_locale": "vot", "in_benchmark": false }, { "bcp_47": "gez", "speakers": 0, "language_name": "Geez", "autonym": "Geez", "family": "Afro-Asiatic", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "osa", "speakers": 0, "language_name": "Osage", "autonym": "𐓏𐓘𐓻𐓘𐓻𐓟", "family": "Siouan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "rgn", "speakers": 0, "language_name": "Romagnol", "autonym": "Romagnol", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cu", "speakers": 0, "language_name": "Church Slavic", "autonym": "Church Slavic", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "sgs", "speakers": 0, "language_name": "Samogitian", "autonym": "Samogitian", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "ann", "speakers": 0, "language_name": "Obolo", "autonym": "Obolo", "family": "Atlantic-Congo", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cic", "speakers": 0, "language_name": "Chickasaw", "autonym": "Chikashshanompaʼ", "family": "Muskogean", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "cad", "speakers": 0, "language_name": "Caddo", "autonym": "Caddo", "family": "Caddoan", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false }, { "bcp_47": "pfl", "speakers": 0, "language_name": "Palatine German", "autonym": "Palatine German", "family": "Indo-European", "flores_path": null, "fleurs_tag": null, "commonvoice_hours": null, "commonvoice_locale": null, "in_benchmark": false } ], "models": [ { "id": "meta-llama/llama-4-maverick", "name": "Llama 4 Maverick", "provider_name": "Meta", "cost": 0.6, "hf_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "size": 401583781376.0, "type": "Open", "license": "Other", "creation_date": "2025-04-01" }, { "id": "meta-llama/llama-3.3-70b-instruct", "name": "Llama 3.3 70B Instruct", "provider_name": "Meta", "cost": 0.25, "hf_id": "meta-llama/Llama-3.3-70B-Instruct", "size": 70553706496.0, "type": "Open", "license": "Llama3.3", "creation_date": "2024-11-26" }, { "id": "meta-llama/llama-3.1-70b-instruct", "name": "Llama 3.1 70B Instruct", "provider_name": "Meta", "cost": 0.28, "hf_id": "meta-llama/Llama-3.1-70B-Instruct", "size": 70553706496.0, "type": "Open", "license": "Llama3.1", "creation_date": "2024-07-16" }, { "id": "meta-llama/llama-3-70b-instruct", "name": "Llama 3 70B Instruct", "provider_name": "Meta", "cost": 0.4, "hf_id": "meta-llama/Meta-Llama-3-70B-Instruct", "size": 70553706496.0, "type": "Open", "license": "Llama3", "creation_date": "2024-04-17" }, { "id": "openai/gpt-4.1-mini", "name": "GPT-4.1 Mini", "provider_name": "OpenAI", "cost": 1.6, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2025-04-14" }, { "id": "openai/gpt-4.1-nano", "name": "GPT-4.1 Nano", "provider_name": "OpenAI", "cost": 0.4, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2025-04-14" }, { "id": "openai/gpt-4o-mini", "name": "GPT-4o-mini", "provider_name": "OpenAI", "cost": 0.6, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2024-07-18" }, { "id": "openai/gpt-3.5-turbo-0613", "name": "GPT-3.5 Turbo (older v0613)", "provider_name": "OpenAI", "cost": 2.0, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2024-01-25" }, { "id": "openai/gpt-3.5-turbo", "name": "GPT-3.5 Turbo", "provider_name": "OpenAI", "cost": 1.5, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2023-05-28" }, { "id": "mistralai/mistral-small-3.1-24b-instruct", "name": "Mistral Small 3.1 24B", "provider_name": "Mistral", "cost": 0.3, "hf_id": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "size": 24011361280.0, "type": "Open", "license": "Apache 2.0", "creation_date": "2025-03-11" }, { "id": "mistralai/mistral-saba", "name": "Saba", "provider_name": "Mistral", "cost": 0.6, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2025-02-17" }, { "id": "mistralai/mistral-nemo", "name": "Mistral Nemo", "provider_name": "Mistral", "cost": 0.07, "hf_id": "mistralai/Mistral-Nemo-Instruct-2407", "size": 12247782400.0, "type": "Open", "license": "Apache 2.0", "creation_date": "2024-07-17" }, { "id": "google/gemini-2.5-flash-preview", "name": "Gemini 2.5 Flash Preview", "provider_name": "Google", "cost": 0.6, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2025-04-17" }, { "id": "google/gemini-2.0-flash-lite-001", "name": "Gemini 2.0 Flash Lite", "provider_name": "Google", "cost": 0.3, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2025-02-25" }, { "id": "google/gemma-3-27b-it", "name": "Gemma 3 27B", "provider_name": "Google", "cost": 0.2, "hf_id": "google/gemma-3-27b-it", "size": 27432406640.0, "type": "Open", "license": "Gemma", "creation_date": "2025-03-01" }, { "id": "deepseek/deepseek-chat-v3-0324", "name": "DeepSeek V3 0324", "provider_name": "DeepSeek", "cost": 1.1, "hf_id": "deepseek-ai/DeepSeek-V3-0324", "size": 684531386000.0, "type": "Open", "license": "Mit", "creation_date": "2025-03-24" }, { "id": "deepseek/deepseek-chat", "name": "DeepSeek V3", "provider_name": "DeepSeek", "cost": 0.89, "hf_id": "deepseek-ai/DeepSeek-V3", "size": 684531386000.0, "type": "Open", "license": "", "creation_date": "2024-12-25" }, { "id": "microsoft/phi-4", "name": "Phi 4", "provider_name": "Microsoft", "cost": 0.14, "hf_id": "microsoft/phi-4", "size": 14659507200.0, "type": "Open", "license": "Mit", "creation_date": "2024-12-11" }, { "id": "microsoft/phi-4-multimodal-instruct", "name": "Phi 4 Multimodal Instruct", "provider_name": "Microsoft", "cost": 0.1, "hf_id": "microsoft/Phi-4-multimodal-instruct", "size": 5574460384.0, "type": "Open", "license": "Mit", "creation_date": "2025-02-24" }, { "id": "amazon/nova-micro-v1", "name": "Nova Micro 1.0", "provider_name": "Amazon", "cost": 0.14, "hf_id": null, "size": null, "type": "Commercial", "license": null, "creation_date": "2024-12-05" } ], "scores": [ { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5592169701176339, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7187320759449207, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4438455475739657, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6320800718582147, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5894973558751632, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7562097956860054, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3846086976522069, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5835344719191324, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4440401202498867, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.634367011980859, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5068360865084963, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6984477545886919, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5679608237702286, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.746881923400435, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.33931070790731876, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5427607577375184, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.33100023927532657, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5283894635872319, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3472596783998825, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5880210095195896, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.49602824624416075, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6821172236213218, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.2511517944602615, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4484633445384819, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5767974034153417, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7416604155998838, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5749603738163459, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7240488251574404, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5617561349997696, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7132694856647042, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.6303545030576861, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.77785134764153, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5812269906647429, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7632349489047001, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3604302813636731, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5648482391867907, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15317719477157257, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.38800976493585004, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.6001453932849357, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.762029391170019, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3742128962272385, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5924994297544066, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.32063971770635635, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5206258401513325, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.39086127104761287, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6239956806265569, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3020679767949182, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5246291817407542, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3629639414033421, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5313865724318225, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19685996214444484, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.45295467854325566, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.30676942927198475, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4968492831219663, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3671596072089024, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5953389856441371, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3671596072089024, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5953389856441371, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2516114673955893, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5164808837319497, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3276399373163712, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5131503736358733, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.23343658187420896, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5188968707275573, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.39544143038459856, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5959322291414695, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2596939072050362, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4394574387008692, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.4273817965049865, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6016204186733703, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3972267643943283, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5952617863931118, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3930690372081822, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6043335353470877, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.32374956399799487, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5552439191255761, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2777551012631926, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.49423240120783246, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.8780634320789833, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.926946700115022, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.7964573357809173, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8458636471716781, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9452996322890763, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9463396364218181, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.8781548422306138, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9156314785041992, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.8562379115188704, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.914880147320643, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.7086626689681226, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8167266341909933, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6537803976048806, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7742226743967544, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.9577952806172931, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.9847675380468571, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.738238064391125, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8637738769684485, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32406433662077544, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5243586266504104, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.34633672321253084, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5378805625051344, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3852076286218103, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5629822759777402, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.26021014514167856, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4820043660869366, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3207234978095439, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4977201243943551, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2755180390863056, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.45513546372451297, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4226799078177409, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5651672709988255, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.20596702648945656, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43080958860183666, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2057575468480153, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43186109332677985, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2502214193201532, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.49819657249183386, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.28925821076686087, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5172170138888198, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.19539650323609742, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43705356257534755, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.498027570572246, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6323394518481261, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.41019145639667887, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5550063659734302, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.441464946158803, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6003092613714627, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3232734746803988, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5256417654956012, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4338913033745421, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6021209112384719, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2833191488478096, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4778413511597435, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13576358182705253, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.41529193531769876, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.24926331918525627, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4599756430080559, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4318843329340524, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6011096108554106, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3582301850807646, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5380305837807603, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44175593938589236, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6111096352841461, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3905612192964119, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5861956606716949, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4354870567552493, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6005516255183536, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3688167255318499, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5626506837530694, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5077888484472814, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6493197366069867, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3935566429569304, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5739224928184342, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4113107630914792, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6024368113718255, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.388275825650142, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5946895227088745, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.422553348837848, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5840904424340781, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.24177360091172484, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.46999682982170327, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5946872253540679, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7456034598536061, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.36819813355629544, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5359192371665321, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.47840604738578085, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6297473901472479, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5009380663759289, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6679481474132949, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4535479195319991, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6276625295274986, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.38827890681861416, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5625611809933323, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2087397501881324, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39410069470509135, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4640742081615844, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6372680189651158, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4641883721676649, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6403267149729506, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.300740577257699, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5272774705181614, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4061066499716187, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6080346530552228, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.31520390441828733, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5666753970394321, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.40454825028023833, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5951482608075656, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.30290762996936516, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5118703718099534, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3732667150787326, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5674650482249737, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.27292771734066346, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5212657903012956, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2736066918197224, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.514117258748181, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2426576141982896, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4681164293806726, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3464618221511632, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5286087759223264, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.13337282396479677, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4379609517006709, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.46238620976190176, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6294498584668344, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3186774371729279, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5594486931861122, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3725907668893922, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5838909337906717, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.46418585410212687, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6257813924169782, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.43058052532641716, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5975873581943051, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.0006956037840845855, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.21346660402255854, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4749873824263006, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3284656616594502, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5314089060682492, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4422044705926463, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6089032707320831, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3099603853356145, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5209233176748354, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.30939216619448856, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5208328629222005, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2417404985264926, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4540589962283635, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.344338817815182, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.534136089789678, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3146876332155584, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5132307789796908, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3576035471132581, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5426399702952437, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.24915993462248331, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4396481537491334, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.24192108083438388, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4175394768692251, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2840596414449913, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4892722276483434, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.28677829776706215, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5017473465626182, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.253492999601661, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5066198263682749, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3968190443102714, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5978315904237319, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3231223153895219, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5181020767289912, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.344338817815182, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5355920179313903, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.28716979381420105, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5171262478660463, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.28716979381420105, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5143386556316146, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.25970562893843707, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4734691139529827, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.05448112815049329, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3360010226928493, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5216531073745614, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4331131003868224, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5898969623074624, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.35580399268816465, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5392592206305507, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.40724702386633355, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5650294312072152, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3741026207881868, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5834523243646894, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.39387637515513285, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5909459753994141, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4116786321664925, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5837404006033683, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.33210944907163426, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5289420578289948, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.23037101973672552, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4814028637155758, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.23922316498050586, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.44705223970825275, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3909683536530208, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5861999156017297, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.406520102973592, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5957668554688678, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.001982553528945282, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4692988665122676, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6232055062803948, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.38914560772865003, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5725189583566723, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4100880948326119, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5748650910980349, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.553414625382002, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7074940030211, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.5215309394772263, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6680522998193752, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.30181997280390516, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.49784375185665214, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.19250412598108757, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4448372401459185, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3109333640704356, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5072760587388273, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5274220384037692, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6765588140322357, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.39317381456022266, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6026058740561834, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3229030611977504, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5136703373168134, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3113772787307771, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5344680037267059, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4015176110768588, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5570033941527084, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.38857454128250113, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.568493737147045, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4475435253337274, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5956867226653717, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2634713516356232, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.48530293133680297, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.27197487450984753, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.49912608327888125, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.35103160282487145, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5432217848942439, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3940944668383663, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5436661645656922, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.18405105316121032, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.44249774237178774, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5815914780944419, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7321831383933567, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4451909305935609, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5879542667474525, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4831574055451935, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6238976883927624, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3667951090093586, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.574382729364071, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4069863197589215, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5748668902054292, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.32926293944513546, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5443707654946067, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0895824671662166, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.24679712992918926, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3511508047578372, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.502364219831564, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.42734667499155, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6397906518456509, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.48930936408255293, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.699085629239476, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.49517040114696814, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.672650019344124, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.47426274497383164, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6547171931962555, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5534262126390082, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7517262392757741, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.39116961050753873, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6565815107523159, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4166560818400039, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6515522498665886, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.42759222581369355, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6292567445430434, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.40493924631497547, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.619667547537019, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.44697138732796604, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6533822343227146, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4699943434621447, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7050475306353289, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.36720541083887626, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.556299558101958, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.45761264167159527, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6880668163480468, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4800491211460759, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7058154381442389, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5803563388252858, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7397216312303552, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.45495679780282583, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.699735222419999, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.45495679780282583, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.699735222419999, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4396453171706368, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6386415226511408, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0025767494884759577, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.022849655955591117, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.49179307081132717, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6798382116037067, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.36921945860245514, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5602656572610939, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3963410285961713, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.613166190285915, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.390589858528132, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5498108214680063, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.33433503990805974, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5465517653500693, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.45096237059550953, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6276175882237706, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.33599052457705525, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5506683357790431, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.37224644590020084, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5716341952568125, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.39141668922302714, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.592604953206805, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.36488503551800366, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5723243480372939, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2820342917142487, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5410881356746259, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.41595343891606124, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6228483474103623, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3647006103716475, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5752487475212197, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.5444545010896156, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6995635476507981, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.44751671242344965, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6011479673559094, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.4611551555069207, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6294324146720465, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.41865363173987147, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6246787832833863, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.4510663025172895, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6439430694122988, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.28278985838873544, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5364084166509312, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.18474062565700086, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3944315616553734, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.4044350002821056, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5937440273149751, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4404175157492415, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6499400950194552, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.44294247711132617, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5915660675216782, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.418987297037058, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5748791698084322, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2020983719878774, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4110516731487298, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.29705368433365786, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5186257965942541, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3497458686123802, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5486997385559668, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3660623361610902, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5840165124966731, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2667148788792994, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5186154099951347, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2667148788792994, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5186154099951347, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3495696951007327, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5497542561082874, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.17509359925241916, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08875218317184876, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3759098347425247, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5116576338831017, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6761326472499163, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4042355060018226, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5567844610331302, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4342485684315921, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5862756549666985, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.32846260295658253, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5234687470369108, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3709295124087965, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5443097614366986, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3415769856419364, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.555003404573853, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0626814220834104, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2649283376124583, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3504606692020456, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5696982139616064, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.40306183496110326, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6065077241830509, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3756985486608933, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5991443770283833, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3437925129268647, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5496158439811546, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4457795438900481, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6608358312257032, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.501322654905737, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6749353853594616, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.41109781447793037, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5909828034438983, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.500516497336299, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7019407549121803, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3422590336943533, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5784088566089314, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.36382507187110075, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5597199178753666, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4389167617930115, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6283965584123504, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4783304729406064, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6570361507659167, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.31791964488124513, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5391165577881754, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4805240060295435, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6678968008486404, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4870178700768381, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6571420749199969, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4544549777519972, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6588011478075102, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4720654627116666, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6517469394467796, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5253138252916816, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.713708032136132, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.36216295932014775, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5817525999349799, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.13081443497119305, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.417733523030983, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5333753443479871, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6915993702819169, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4892530408936975, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6697286007212407, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5009456904181451, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6893719644090858, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5011800954736271, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6882325337556615, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.42451113499289145, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6326418045965277, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4307886337606128, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5983383363156769, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.464941535335407, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6614464392132021, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4824471894538444, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6756807439055712, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.42913085819666935, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6230860315754777, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.42906677303047097, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6259670174303734, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.47347369701789205, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.681786235656136, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5335035739559317, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7040649389679675, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.3655292171929706, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5818586474198358, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5963279752582172, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7384834127486712, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5416689002024996, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7032606089138365, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5043550869731553, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6689462373151898, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4628513442989428, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6651586361790265, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.524431720527746, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7076771205887638, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.48840342566834705, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6801218410948642, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.004953764861294584, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.48578120610890896, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6418878687312928, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.498687604330117, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6495577010231699, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.18273944860385094, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.44261865187418153, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1921021633645501, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.41090634933708026, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2019984490972421, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.42969616197156246, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23555001457110075, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4328470748839584, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.19979408064496967, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.44501420508709394, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23363375253301555, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4539275409654266, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.30081934992431447, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5592925653127773, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2871484146452821, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5435042611894851, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.24058995161649158, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4522509933949415, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.27552516390390885, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4769491782857059, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2263758580444643, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.41910522124347077, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4278755948981275, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6049024929611014, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.18988095581607925, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.41823143717308187, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.34777225435927045, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5603739447290761, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2488577037192601, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4700612059850866, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2858464946739048, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5073688691937708, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.19269477347765157, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.40684209227541773, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.10246901021115776, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.26380432026626405, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4634992426765033, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3897372020625521, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5520780806464591, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2153742037697241, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4581737688885401, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.22583314893598608, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4634872123809323, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2000682107464079, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.42213947952783815, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2221644327559588, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.42764590771808364, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.17877584235677071, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.401518876879992, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.30519601919508343, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.48440897375540304, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.10957715528160569, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3392444984825636, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.10964882554034484, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3356389160000376, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.22347194598034506, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4665650707763161, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3016964931112797, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4535427413316391, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1911861015937895, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.41477093415943017, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.4469358090476088, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5872096766535113, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.287676448167452, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4733049682606063, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.34059658886569716, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5263364808620599, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.31145364701208733, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5087911718200273, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.31145364701208733, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5087911718200273, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2636532817002844, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.46325989506424586, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.004236700409670164, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3711271620335373, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5606811328336353, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2775751476798985, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5467407840471017, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3372953649368346, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5482505380106469, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3598041249522345, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5672133517600307, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.275788082902897, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4682894376569175, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2898775882071186, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5097463471921362, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2883603713983444, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.508309417496147, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.34655442187135127, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6023567722379627, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2740037448125678, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4683631907729274, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2740037448125678, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4683631907729274, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.25810978038865107, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5114862976334219, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.40268767791422966, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6359049000877419, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.28143597386296987, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.46833203769304566, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.08994455977452934, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.2887022044225924, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3766776485541237, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5833210829022488, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.46443675322751826, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6512173868183774, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4244950970711203, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6318443095842109, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4244950970711203, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6505130874640082, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0922665949962545, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.28952892991876095, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.28612208859224425, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.20955561269928308, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.451252540938088, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2988083057066004, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4973008562914265, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.28528905353056333, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4885812318466243, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35797362976091973, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5379266632230616, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2606045000988204, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4525313379099324, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.3739173814408067, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5300063372835349, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.3626791619232025, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.539836963539224, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2453787991485662, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4099668999237371, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1426882822674975, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.34960972004472946, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.19360049306902116, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.32155751243171055, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5282954234137397, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.29762732722843216, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4476081666669917, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.23545988330717435, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.40601705732690246, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.5051170491729706, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6566114460416413, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35093163714125025, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5161806517116977, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4187059279293422, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5806611969643932, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.42286596174824126, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5934357258501683, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.42071958648966074, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5867954120500313, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.28176232344609076, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.46342775156724203, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.27694098293799824, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.36560991595112396, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.537072365457506, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.35120509380099896, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5127991322787522, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2935204022158406, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4867597973247361, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.36394690002866714, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5567484827579814, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.278704088378991, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4868935860000992, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.30364957397426867, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.490461471023638, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.26416975244160523, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4438864952532326, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3091536050099401, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.504963808447426, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2377283063350729, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4229894191312214, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2595156374159681, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.44692374238325255, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.28644027312006637, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4643839364819269, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3169600089456638, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.49269567715798124, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1905285416851139, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4177320592079303, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.547669734463399, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6920019082878786, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.39070481609556534, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.53793582138906, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.39892980454447485, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5839375286411709, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.23119533406164058, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4549622022003173, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.47187011152614905, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.634570712438076, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.26924245665759383, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.45760881141869997, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1501956901694662, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3435352939078531, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.30692705311222085, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5531231299653412, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.49132868804528823, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6524450166860349, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2929684584911775, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5038324436049059, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3414171640083141, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5306256202657124, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3858101625283812, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5618844078335644, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3718731060476833, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.507920995618425, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3718474296835603, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5563193852397018, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.41613344165345995, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5740077532098984, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.23015479707279926, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4043490475674803, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.17629023372542696, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3473939681613876, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3116287423376191, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4893092447918963, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3761474539770847, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5536622992238994, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2459980185879811, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.47485821292608255, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.4196211376031888, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5915995690152394, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3785127547760706, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5548613310192737, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.40983351958195835, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5980339788644404, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.40840960406849836, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5662632887734669, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.40772967686463607, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5681891080404556, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3627861053524045, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.524896354547667, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.047201037160775325, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.12237706077959995, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.40939284504147777, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5645111896180985, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.27106784138456536, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.458287745564531, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4034224234291925, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5736798834726872, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.47117590712234436, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6157183058759933, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4840329060094462, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6570537611908611, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.5211295957876436, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6543358670735736, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3844723738020861, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5612506236862517, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.49428478171113605, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6360862650323953, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.30384210838236353, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.517369863710813, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.30384210838236353, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.517369863710813, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.33677049851999397, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5762640586619034, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4134997467039312, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5981100031486645, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.19080206844973818, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4451297657136166, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.6611893921112539, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7385527846626787, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.5472843613586278, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6462543667959997, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.48936688255103167, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6232884959088987, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.49864013450084044, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6473028953530363, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4705190878543854, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6348294479712023, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.0006449948400412797, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.15688445463098402, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4711705838157902, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6028678286611538, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2822871796543221, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5208915029538709, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1077205146963877, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.428338145564396, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.09543667505391068, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.40518998504409354, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14087022592589463, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.42752370954120755, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3077490672091579, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4982442692170086, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.16660766718834744, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.43821636698725164, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3109058809229358, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5045951829816013, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.31213647387601523, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.556395949945723, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.31213647387601523, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.556395949945723, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.36576182289875453, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5569403582137159, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2987390399566193, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.49080609910208733, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.12121103811203453, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.36654749330221426, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4872311075347288, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6623535404713097, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2757545333222742, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4738441342217875, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28983869034423043, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4975732770770436, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28060741458208943, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.496580338229036, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3681900464793093, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5504673899427779, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.22107379072983208, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4472044729711229, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.07383026958055552, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.18582113429299857, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.32814442346427775, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5149345446415335, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4102082155233312, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5474039587505726, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22327767951697297, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4063556880747369, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.26234851988380015, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4686295191568941, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22472032138500259, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4363253004030211, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.26999626626742373, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4462786481475064, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.1523726019659672, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4249945948121055, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2556346494160282, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4538035440310274, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22094141139283613, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4436055020535846, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22094141139283613, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4436055020535846, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.14283509516492696, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.39080133039424786, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2671559406638062, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4577424762656183, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.002106149957877001, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.43636719577147937, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5525891004904828, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2512606392489611, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4210700546502019, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3284145915841146, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4777770768413136, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.32565974985390567, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5028101514284876, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2993726298551646, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4773135617112927, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2507373945601762, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.45285904278083683, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.29187222866434104, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.20649207653440943, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.45559573554011507, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.22424453668984448, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.41637444107955873, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2572733200413211, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4520014138562526, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.23112644289004342, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4228120750850924, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1733396766438206, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.37157614360073693, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.27884029427402307, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4808977586027471, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2472606041939042, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.45364472696939645, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2392120773016637, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.440445343487272, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.27477175237607115, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4670076076385746, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.21038351069657651, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4170983383308206, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3070946890889356, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5150001444865586, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2393813524637459, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.42382875320112184, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.18439115006412007, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3881716916328596, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.4484493594130144, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6392061930349952, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.29277567814514704, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.47534798335753625, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.34077616827498786, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5278331664063162, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.31260047665100127, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.48667320069984316, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3024740132924786, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4860481290671275, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.21472597489801595, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4190785642335582, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.05624172669013078, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3317185957958262, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2624355454690498, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.48887901649623144, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.40165053057541866, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5837756195280097, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.40311197004738203, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5788525108956781, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.30912713581280643, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5376618148723133, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.22800071662764984, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4763467106828393, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.42740890037960316, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5996769756257465, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.32407268851096743, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5123210866097154, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.40487199173556226, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5637204315528265, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.19864358811190305, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4520034758289839, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.28515736078765247, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5144923375933018, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2997057270104923, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5028660357670663, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.35016444607906333, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5318969359864418, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.25497731326689277, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5321857015823233, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.5138735427755269, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6711767933025353, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.48917248258655954, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6007992381101284, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.45074681913051867, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5985843659278748, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3442651325185116, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.534774838547693, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.37779254144801305, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5639615032285982, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3411216349302383, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.524533707137854, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.13496104417905996, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.36516261117337495, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5425947356911068, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.49872195941208947, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6907054265096231, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.45313578977486535, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6160993561903745, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.37640646218183, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5429063669356702, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4331983607416391, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.601662300924314, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.49310399113262143, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6618877666161819, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.46511244412293995, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6535569144390859, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5108628809804742, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6929396211173784, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.41336688870747906, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5851805477143694, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.38942582033344114, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5648719586230837, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4485994475252126, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6258984728025891, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.543805702633007, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.7108467686156834, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.27230544563000586, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.511482380897768, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5629805730671188, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.7184729617045537, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5392691323275658, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6950593236840004, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5248291448433852, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6920934053021797, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.425742897803471, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6292455373063424, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5098155570066008, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6842801799859595, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.410248141700974, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6198489533513304, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0072148746031117554, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.09496152255049971, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4803498024083505, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5963395991179793, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3411271681324882, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5323123267352375, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2651736858432996, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4491383344282561, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3082082660061424, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5077609645706764, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.32151064813737534, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5058205933378546, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3292501961779507, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5076613847693546, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.31723554000172904, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5055205673212141, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3335262554878992, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5258955094447381, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3516912179205685, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5464920089233378, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.34757716262783495, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5456290989918442, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30384210838236353, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49573162353290035, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.34046691946402124, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.529497944319035, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.20857446308936162, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.46466122673467003, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.4213151123885409, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6348713285352305, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3215895303258089, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49179447692232336, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3007845437586152, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4720170373660879, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.35069370820755275, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5735580981959628, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3559980252477847, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5455195296019626, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30567695364499425, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4994609495460993, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.0014196479273140264, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.27579736884967815, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.44560520221877703, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.24828430598240606, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5078550622606068, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.34545319957597864, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5727052860304503, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4256604038587669, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.595254482532169, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.35948829980203323, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5639910704472698, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4383332081326208, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.606835521790659, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4706737586086326, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6417233649435136, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.37742688647401873, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5674314405993244, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.30233255481828714, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5203155278990113, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.35770998339980664, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.581833855035677, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3625286446151028, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6148737881972042, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4012050186129501, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.624957701947079, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.37050354724951784, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5886100035095279, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4827832239649112, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6550149284488518, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.49745618936962227, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6671359503342716, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4519603667438429, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6009987666643928, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.5542271267412462, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7275049499508799, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4878448947255055, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6426554193783609, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4345206442085496, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6585506298716566, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.327910616954487, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5832612672351287, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.5350666712285949, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6501051146578934, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4381699512774638, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5887410281104106, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.38968867962607934, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5581403039390647, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.44378279372807367, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5825113284353328, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.34093060419986554, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5050414552947896, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4312966248043606, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5796681637399156, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.35491112745119674, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5468570448895366, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.339818403012025, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5156759219303986, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3521993875851369, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.539388626519818, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.30451244884661904, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5270886236273997, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.32155220285195785, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5502401579986564, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4173085585041339, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5601628790215745, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.17519022150205726, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3999732122899595, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.5730497086675282, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7127638643645163, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3981933677617053, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5407088037569207, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4647350187265495, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6141693179612359, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.38621174932063007, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5629586598269498, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4173085585041339, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.572728665781863, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4031413391988539, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5857356072592188, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.431633629801714, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5611890334237722, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.17727473966694943, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3475071694578125, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.20451416608402828, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.38185285396290036, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24678030799496634, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4463603005685723, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.17736142488062245, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3654025502565916, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.20739970432549085, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.42437033953049846, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.10962812839170834, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3474392467819317, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.12843096555088776, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3356201430079791, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.09963289028859902, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3282252226526078, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1304767107567893, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.31187491537917433, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.14222939605129875, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.32212719342865237, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2530426809357554, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4243735004657182, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.23231698016646643, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3975460179474858, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.31347763183631233, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5290306159372288, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.21424220062855565, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.419670209137084, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24809323900653618, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.455254011012136, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.22798424876104878, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4315883077530936, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.19800382589668103, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.39444773256270804, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.18542575245571596, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3788879537776753, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.0013506212857914643, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.22750547588410633, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4160796302144522, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.5494025263062274, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6860161543947312, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2636405082687104, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5072009470421238, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3994138413590059, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6335699196668345, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.32440820201863096, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5816024759666973, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.34337934672029974, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5312561179539695, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.4403035618887612, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6631416039442045, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3536676112393946, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5252283198216768, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.19029342592119838, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.46626570553905117, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.19029342592119838, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4672523665085142, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.30860365223174097, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5323991480984563, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.41255466997762913, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6386796139644701, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.27779829164283953, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5451746888418362, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.5747867448954953, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7236969475311006, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.5046818724935341, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6768618695861154, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.4698824517223119, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6509974368827985, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.465943811426769, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.646929348297808, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47785728909212377, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.688922443358261, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.34423833594189435, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.576428944148875, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.001973164956590371, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.39626726411474644, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5928013371853409, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.4222656487192343, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6421614792137705, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20174173621464261, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5179166118048267, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5116634146141776, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6950231685488834, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.27720246067551324, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.543353961410956, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.4509728065040443, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6500555759069969, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2481045172535937, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5296542200314776, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2348553453946444, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4891959123914518, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.18939338506411268, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.49051459363589717, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.07066046637883687, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3470742306712029, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1658317981046275, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4396479745504188, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.18943569604789887, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.45232508607731536, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0051795097123194895, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.0769184040221202, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5030879352944162, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6846791297914651, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5055953275836201, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6788641233135904, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.42072143291659103, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6265956117333142, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5079711118438801, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6900890595896133, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.44456824349458923, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6567673471796899, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1258024774154196, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.39536132018550907, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.07446712399912313, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.30485244492635144, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3394216003840941, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5399361239256494, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.353179331599201, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5558881348090785, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.33522833358360765, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.534195929930943, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3279338213872338, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5206722319482356, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1900249500296748, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4570054063295732, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3417785003224633, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5213383973963687, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.33082955843497286, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5333110333825679, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3461114139111442, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5537111972654953, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2753998085739322, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5086546717198241, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.29736692860269925, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5307507954839085, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.389868366744335, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6181891240638018, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3666868345821895, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5683418005578137, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1725434802959889, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4679048179971906, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.5181493032572185, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6641637236851636, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3559980252477847, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5099636935342754, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.37858398735109683, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5535757116038853, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3201978307646018, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5281184078781382, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.41470071559182964, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6136976280042111, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.020243598198744116, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.22949385525084642, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1627842130495941, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3513085830979839, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.30576442771176066, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5175418593642837, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.4397415106513502, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5907735810868658, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.31308824228412185, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4950165423717857, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.28646584019908145, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4746124656486252, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.21240535233702176, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3985917300395283, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.4261122398801008, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5780599654568969, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.24013077509836228, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.45691689611827113, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.3734491516745214, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5499493819792871, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.11197425295329791, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.34192899545806504, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.08586319437724399, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.28186139496120405, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.18416226663843008, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.02935045498987271, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.18487351069843888, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.16506895155186319, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.44783369619727237, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6267235013545246, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.31385387863650493, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4830034520070859, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.030041173262958625, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.16461275738712375, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.28710736118585223, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.47019373110040275, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.324978583787703, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5176680074900262, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1527358476261763, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.37130823751862757, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.02574148824389794, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2111955699760469, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.428831679677381, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.46890796443667687, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6445795993451092, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.30704694388456133, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5217468869740803, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3675770737978913, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5833872029429698, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2381080412543041, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4678770958208047, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4648698750879596, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6377045673268608, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3558905194860598, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5570369132115492, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3612717557348476, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5558371668340614, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1619935148676164, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4271616542112861, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.15992948177167177, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.42371338929019253, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.12508074021419405, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.39088781423976093, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2501291156194984, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4242027531340573, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.10727279557648407, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.33374335628033724, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.5488130346879996, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.720419730625973, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4269590215068612, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6090516838507328, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3699375619378516, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5932397042974766, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4346391355101555, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.648783727613815, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3994868082159731, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6159441456463444, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.0013854253255749516, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.24647819790998704, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4673628408395248, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.35045670972629744, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.564796827816794, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.07407154448063642, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.43145434527321425, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.12903696060775005, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.456225988032654, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.024459391267874976, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.12351824822447692, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.46822754470803873, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.16221060929249448, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5093553101634974, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4463892736716987, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15815751066481462, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5152611872266766, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.14461769822288426, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4699313689038472, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.14461769822288426, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4699313689038472, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4031456247133876, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15865962437786532, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5308758516723786, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.08516700886866406, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4091252890943268, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1583163321869008, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5032511267062394, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4370196290761142, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.20669086265781264, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5076721272198604, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15611634095633747, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5075814499747183, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.11552841238377509, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.41545719136805614, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.14679153443080498, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.43723267444847275, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4122750002638689, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15412719160788987, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5010353699512481, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.06647168102389285, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.34350832619898364, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.12560672881768975, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4969560260291519, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17077058518804336, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5022008374701596, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10784756064735967, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4427230465401631, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.079733958307467, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.44184113874318065, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.05534265631745826, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.39688946206212833, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.12369892692249995, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.44549610902403686, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.14876360706338185, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.48334700075785475, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.14816972851445565, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4827506956539706, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.06656213940646748, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.38435741328258305, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0919956586924294, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4320605493117323, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.42723260976616784, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.42954139521687473, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3532931581623198, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.175396614619324, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.49736499605529066, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1609675245202845, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5069863833094232, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.39861856844560895, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10802866550123454, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4137246391706996, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4041678259311437, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1290514243115152, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4766581477336301, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.09735981717515908, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.35288934658906385, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.08273178236238297, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.36399666460809255, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.13012870333257068, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3852835519852091, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3356633416447032, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.09656914574218514, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.38029971714040783, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.09553543457519309, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3531525294256142, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12422788549118892, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.40222210564426, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12020040946693893, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.42011426633442717, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12020040946693893, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.42011426633442717, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.28789057461471257, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.11453355784159679, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3913231805957233, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.058502903451539655, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.31167095759390945, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1568418931847707, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.41485110412488607, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.08628172140775388, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.40272097867515005, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.10467757347424328, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.36749853206282146, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.13026649757585426, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.41550755035304077, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.07102549926281305, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.36283847689753107, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.07771118177065015, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.34810630778111895, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.039782861678265974, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1175904695048123, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3996881234028031, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.11564012893219777, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.44599783682350064, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.12601482779921785, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43595665254608706, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.12022286401047096, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.48279986805368713, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.15350377490367967, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.47645148444499064, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4329131730483987, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4042977714165801, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13714845589364738, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.45499281593451946, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.15187655550578968, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4991359434734445, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.15187655550578968, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4991359434734445, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.38785209659947417, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.07880540498630446, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43116404282677934, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.08174633970003824, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4119415264378122, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43122763125947844, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.07593921750963317, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.459811901287104, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.12848168928706002, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4421263683867116, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.09198045184317984, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4598393646838097, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13191941029086238, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4054693592509284, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.10246963414578486, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40167806467929934, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.07798530247118374, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4006113700211268, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.14541923959059266, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.47577612932999147, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.2521233582161207, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.40959087443621306, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6348509381122925, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.40959087443621306, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6348509381122925, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3182970443542658, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5953162569846108, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.21544268192394778, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5620944560874692, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.22238763863547817, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5765887803460186, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3026566818840519, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5945859352092411, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3939307348079401, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.620481013358287, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3939307348079401, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.620481013358287, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18816868192268246, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5179253053631742, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.40959087443621306, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6348509381122925, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3433850255029819, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6024262111925348, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.23522101642407195, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5302138314227511, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.10416245702438577, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.464679503899398, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.09629060614977814, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.43565498999747165, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.28418123342684043, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.539816402671069, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.23664926064855632, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5547657702782856, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18721276943014145, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5089836023745591, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3765959322920135, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6295826606382191, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.40801269202545287, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6210533025653295, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0867932999243575, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4201964133235075, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.08214106568089705, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3969463877642616, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1897299381066278, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5086851537953713, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3833939462124923, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.08296825794514656, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.38492923596577555, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.06036796843527163, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.37581426760977427, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.07793031063789554, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3700181221537743, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.10204728251899628, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.32811536740958436, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1072035287734848, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.38653021859049697, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2718653389257641, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.13784847984621976, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.38056078135358473, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.06831564014494437, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4551974335055929, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.09866644266774938, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4285845620274377, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3327209336079636, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1777835117834348, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5166806073547074, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4056741942217607, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3500358865894883, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.009396473650937872, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.13582906387565688, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.43344913217266734, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3630576975795868, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0744904632040495, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4111163205685468, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4363130300030932, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.41747276065817185, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4278386148807753, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.401865675252717, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.41649654108052436, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.42978885796805627, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.42978885796805627, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.07749370908741021, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3853293582383978, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4303918965149948, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.36273754948571285, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.08025555322499443, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.40116594181297777, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.43416784832299543, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.43622390508229153, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4250905063113662, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3674996461080071, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.39174006736497724, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.36347800793516216, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.06254678076846341, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3887428577633272, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08616711094288851, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3696512763473903, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.12894104034845807, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4486368934849452, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08825252192863794, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4377853721520782, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.05345137572833361, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3829169125379508, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4024696872829392, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3404791678264965, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08767210132815903, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.40476518002703893, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.16673716541498604, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.45694863486516263, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.13578223194911257, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4091221496995749, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.05422898988559086, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.335890201952113, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.06482491239183016, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3859593133534678, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3916659692165871, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08465714266003518, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.41240280272579144, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.074350530956551, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4346408669855704, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.34617921188455225, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.10186730973904586, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.43665642120840553, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.06552322707010354, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3576301367090791, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3731922614950606, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08248974616169381, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.40456777770242314, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.10496714075880566, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4262440114275301, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15386029327005746, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.43911482594829104, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.10070927557742705, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.43718220262892105, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.11478463129234825, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4651957501593415, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.07137101582673294, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4075406301092705, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0846581996011045, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.45098657687728133, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.09107675218561961, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4297036775694859, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.14738500064905094, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4659728395318289, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.16934590059353366, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.48466724462095995, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.16934590059353366, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.48466724462095995, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0643329477522681, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3960585990192623, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.06883375756323683, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4079414323089176, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.06225053846006199, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.33576700828174977, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1262345212021199, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4305259421555756, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4502540674899478, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.17247941414020762, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.48320144379865687, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.09751270821852938, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.395617758442078, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.07222350715877336, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.40189924507920805, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.05534265631745826, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.37576775323350164, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.06301432444316532, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4249725532507508, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.18248753930464637, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4759830743101189, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.1946966569103724, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0772718393063023, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4203683137304257, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.08291357159799752, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4009694996956877, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3714280466838255, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.08899053269919978, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.402294028439773, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.10639077953820089, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.44452351549730684, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3370100422576744, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.38053031314827857, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3984985732544162, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3538602132402044, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.11741368553792744, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4489574295483002, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.35993446555861985, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.09058017202418268, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.45761691752578293, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.10490867528469339, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4381872831026742, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.167672929900467, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.46910779766306765, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.47435308668900444, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.40661291646126535, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.07675188745183982, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.39855715351628995, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.08351211898903935, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.33030812447506436, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.07528927678469202, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.422513417362817, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.06126604215610123, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3837677428398438, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0756907193511249, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4138725093679467, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.08866637424249016, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.44876462229383973, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.10574428430204418, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.45371814600333005, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.439334057339686, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4351068027997583, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.09084091756463074, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4286741659142759, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.11107006417963905, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4423176833595632, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.11107006417963905, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4423176833595632, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3980589439671235, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.42773026235308964, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4186723698262335, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4357976697626214, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.07649636372749224, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4589644893179388, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.12649672885841734, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.41329609863930566, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.1219449069656942, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4776943038671049, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.09300616718241356, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.380268508362473, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3692592582677176, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4606409590817001, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.07996209785853586, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4279137012019699, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.1195053737774238, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4512136289975786, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21748353646757182, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4462746462826943, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24443999371485628, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4991016392840656, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.34155562837143877, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08890843444834641, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.39748122457895574, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.07977475994840084, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.41362647590171586, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.16764957347186446, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2291132016494709, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.49134530869146475, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2291132016494709, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.49134530869146475, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.1139393935967296, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.0008893632159373888, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.11020939962740195, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.12405768590988119, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.40898021337964235, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4077774235667367, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.1701935252826955, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4455315745640286, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08932983819566953, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.412238728569517, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.10358885722770769, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3618355571813406, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0726047699057895, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.33507193065564506, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.35698569920901285, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.1275291133503835, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4127884601900206, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3538966478758119, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4179644538349004, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.11116091368823534, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.43307401079748475, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.07649978886725356, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.41031664319131844, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.43422015530849367, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3867446668969619, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4331286519146886, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4168975501651573, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4173686438800703, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2626949949898101, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.07209415755182004, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.34065919239335857, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.058344823927322736, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.30347089460185506, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4345822107320723, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.38287207799051226, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3795844422349344, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.07012053105310272, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3123716745719453, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.07237963612631294, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3405017838508768, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3681425965156976, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3856352748003268, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0876062628502436, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3978552283854932, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.43759229210123524, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.10505106462290037, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4474870048911137, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.11534976570369744, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.46761329904761845, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0487561532099542, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3938156291645021, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.43501677302784214, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4423346652606821, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.11378204941109882, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4981472095171313, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.09058017202418268, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.47296709670964904, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.09058017202418268, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.47296709670964904, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4098374118843212, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.42966148400813586, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.36147677376770687, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4537465621062763, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.07409363550896995, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4967565970170675, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.11335203496873462, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.46528080200591054, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.108829546976023, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4177339268402449, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.10755896992103141, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4020332959926386, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.10561393446836936, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.36231548741660335, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.008776218574747889, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.09026606980896171, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4602880143145438, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4239838444198129, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.0009218289085545725, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.14883746844067872, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4476843235219058, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.07999819990926477, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3889987132692464, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.45182850108544576, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.06058139791899572, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4408463415099943, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1059352062327485, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4291550754056065, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15311852363615847, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4119139452120141, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15311852363615847, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4119139452120141, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3916082207331212, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4665993963816433, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.05840817340853527, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.35342074486617714, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.08841818041776058, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.47772386173878106, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0678480312173042, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4265201702004798, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.09171389226334559, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.47356776940569145, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4750212573397775, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12038853897576812, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.47362751515777307, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.07875418272655998, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.38690742073333007, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.003607064963668313, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.09577479457615844, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.11161133657801552, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4277891734340718, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3374178992279451, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.15653859793617866, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.43177798053127925, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3848892678578171, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.059281546387121374, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.31614571419525433, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1550056037604323, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.44337732176739364, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.11709058244847056, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4050787124470676, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.15720527174368754, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.47882285385622714, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.09116976904712065, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.40657327142150135, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.09116976904712065, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.40657327142150135, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2973352934874205, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.008495715968558294, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.1018469620835675, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.22915930804797763, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.47714463990739786, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.07925388755947431, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.492179971192686, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.27560832232663307, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5392779492225674, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.42348732385732035, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.40349510205992334, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.06786993616264396, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3421484177024472, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.08302169728235531, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3447730755591614, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.12785320519680665, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.46613459917836336, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.10106439835419144, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.44450926478634867, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0891537192318598, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3970634926176537, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.07992844954996121, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4400081800535333, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.09554681544059333, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.41422485590617925, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.10180993216583333, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4132076508398995, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.08613106833807438, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3975508887703536, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0982484177591637, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4109236039282987, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.08881356213586242, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.43361166925232786, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.07696018952123163, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3952360823843965, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.32015903488199987, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.14691658254161208, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.41606903643662335, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.03929044884480441, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3378344273327324, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0758360142139109, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.375189380253384, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.07649731878156017, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3813049788572602, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.14483568709851755, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.45354858647333196, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.10444675051855158, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.38166524283468484, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0598279319535462, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.36230972213894785, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.056223651641346066, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.34460908274197133, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.021139000776129766, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.11663764605404517, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.41241788679161784, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.052359103292999656, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3805982553288677, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0950136506275681, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4372017487229785, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0946260953698702, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4353772493110627, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.15714515459910894, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.391751004221657, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.42253902305100327, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.16496711525651045, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.15581507331519903, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.1569550310480722, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.11183036824736405, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.000885582713425434, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.0008837044892188052, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.45346064531247376, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.07024127582598716, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.47294267112081245, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.16543976568828428, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.07545713066088315, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.35068174137403757, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.15759802396025455, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3556085508212346, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.1113696974855524, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.07652593079250605, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3602429629880003, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4404222773455128, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1259356760989446, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.44568274520971096, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1643146814613677, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5127730105039489, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.41972158348095406, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.13550937767032326, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.503019099672843, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.42638157008001054, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12506460115047335, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.46140175133635725, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.11765201592537665, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4747275270084755, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.11906127329230787, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.46393002457493004, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3866869165486058, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4729772499029102, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.0009127418765972983, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.13870631856463958, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.48842698915833077, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4238256552423293, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.32485028075459577, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1289863677885349, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.42110704132809784, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.39349347929480366, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.11240015835040616, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.37559985568444276, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.09354237835233341, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4409559217991841, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12748506711468208, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4508210683728834, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10833971870416897, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4467303749319595, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.16322494183480127, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4815584993817062, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.08894652425495941, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.444906007048383, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1029835796838552, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4404518759673606, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.12969927642858944, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.41766761485960235, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3807183676612817, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10127171102984855, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4525620764847558, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.14055612605808399, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4124924918007278, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.13855644267589232, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.402349831140111, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2172505600894225, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.07402253274163141, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.39107772695242055, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3225074204652331, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.45366883374422223, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.07686127660362363, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3776399755648508, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.12826630655689159, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.36561922835086, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.11993418633737256, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4771538581125459, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.370339056755171, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.06018687000243035, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3434593497880224, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.049266699072917926, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10041064691273172, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.44193101759002734, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.09463828889338871, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3398200805270262, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0904087252785689, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.41830513174690515, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.18237761178381828, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4897620961756989, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.13160881951665948, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.47196475148373473, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.19652148611100978, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.46276687134854994, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.14059082344844442, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.45998037393370494, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.14163299203710986, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3958314877752854, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.20815166635049767, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.45544025525531057, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.20815166635049767, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.45544025525531057, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2854365802731815, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.12575185526286148, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4474760312494353, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.05007800213368231, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3609874593707476, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.12906510917536296, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4316039224423657, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.10371256119995112, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4718081522271149, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3339687893627504, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.12408616318856698, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3876257744772486, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.09676840486068537, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4178064649946451, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.31855089109915946, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.13661459309404012, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.07105699030509427, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.40480969933909144, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.17208141302168437, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4542522451167506, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.21351902664706998, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5130443042033361, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.10553179283083523, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4283144779172244, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.10814706353513916, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4216597036907072, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.11283345429772766, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.42059020279539633, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.11757519503939892, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4440750544699183, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1200100437012302, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4636227306109079, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2018735691800057, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.48450292773822007, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.17061515620714754, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4576821112653066, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.38105951101537255, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.08941154865546014, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3829533851946095, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.1950507243360035, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.13942317095527404, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.45935970393208286, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1266453888967545, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4661468774538111, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1785750235950628, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.43344212044851604, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.16508680260754793, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4714504120878508, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.15735432285765638, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.47213324077558755, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.048498602240297534, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3379527543934173, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.07862112679032317, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4059503829406287, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14400312819313033, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.43256046228969486, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.38763756150559275, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.16269986423611488, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.11960636789197196, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4498565343058379, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.06530397960697328, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.36899545840843095, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.14718545479171663, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.460257245015624, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.04028607466240258, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3532348375098816, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.06289570792563275, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3813881170279124, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.09920354550190408, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.39773404106856114, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10026469692688082, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4029197068884237, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.05364480688581678, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3678203159539189, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10293517625804853, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.41656326594825205, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.05484366713129734, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3482099922682012, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10051147382872337, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4554345525110637, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3553498645748245, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.09042147098974282, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.45055351363359086, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.15670253601070666, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4663740399508032, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10313151558812104, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40694354343496913, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.07012817520173896, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3697200811525825, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.08269576405332207, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.38185156188383546, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.05014252780397407, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.38032629067357443, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.2398247112527542, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.06939838145153245, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1384529882948561, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.38277790453523536, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1162066330922535, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3781611496143332, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.08720695571682537, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3539397057594732, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3489532010732457, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.19045679700622437, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4124342444810736, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.13186515857235506, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4331981792485784, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.13020912407699098, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.43037326036891715, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.07454232971572508, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.32060982856396664, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.10685362716233777, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.37718436006223416, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.10236872486556349, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3655843515716045, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4300304626779191, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3423817260769345, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.24120995733605022, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.15969495416406884, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4493675427485572, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.11882576474873885, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4137309803556429, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3052529256805565, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.21229683306385236, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.10500492468363652, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.35306452262726606, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3544628606759813, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3371547585108182, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.347335662744532, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3436708646772823, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.07528359366363899, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3929787160946966, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.06980884340032019, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4119294666395687, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.05275923024775565, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3724723203846839, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.09212221823733983, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4009305712746929, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.09212221823733983, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4009305712746929, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.05182797087573874, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3356084649197975, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.06394979207378956, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.38558242957188676, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.38509368159944835, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.07237989995674375, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.37854508937809583, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3862862497500016, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.08964131615841985, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3962711438859162, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0842991091574967, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.37839472970450666, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.08929303071508352, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3812590700275906, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.37026342464744205, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.021188116207401797, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.059737095980317775, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.33742048813623593, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.09676230489828269, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.43266369498706486, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1691386174483793, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4920789340026317, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.26337200877742073, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5332559901749826, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.12820355595850366, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3621325951848801, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.09626574733625733, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.42477685654731595, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.07980949791887201, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.41420415271817995, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.12650809806003369, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4579202271851988, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1579087295499776, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.45872425820649376, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1579087295499776, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.45872425820649376, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.27031481031630283, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.0008494733265375468, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.06811376279492601, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.39733701209881217, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4580958606533364, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0764396382727319, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.479028094818329, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1348878985611687, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4519788039621858, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.11248337299167142, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.47408452973613896, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.11248337299167142, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.47408452973613896, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.36955183141564213, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.03735667108797313, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.15907551162629324, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4524235916096891, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2356661678654945, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5124350706386419, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.14944432524273302, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4972796478830659, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2128223810599462, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5048999729332083, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2159761642923436, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5016920563570307, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2025321568231461, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.48513287721314796, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.24158268888989357, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5410427858408839, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.19135523280427486, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49947805136320467, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2128223810599462, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5048999729332083, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2128223810599462, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5048999729332083, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.20689377284100188, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.499181874773421, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2128223810599462, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5048999729332083, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2040063460127264, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49119437313905046, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2192257678937897, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4939069969762876, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.19989672437010242, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4954677323302961, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4522625000672462, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.231679638185573, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5128772172047342, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.15455087483252075, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4692608507135787, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.21119143803941876, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5030156541243803, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2128223810599462, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5048999729332083, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.11469202308276233, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.47736356509677796, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.10720391954020723, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.37219605281253065, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.09793316925795417, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4297577431879659, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.10461993210426317, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.411539574168363, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.09232875412879928, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.40574729737089493, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.06106711519028805, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.35756654876490823, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.379821157654799, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.10588612806056373, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4068718481729766, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.10349275234623093, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.39646229864034915, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.10078272841498563, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4064722660884474, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.054115495307563, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3261514049985403, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.38160462422538616, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.09769679999383253, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.34898418602745346, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.12044433900881439, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4241018127470702, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.33260316469843504, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.06986280403265237, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.35513587606181224, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.11511385959745848, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.43904137765866535, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.055494510332021456, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3537313942209114, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.04637573483688681, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.34947742719726066, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.24802563498261762, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.15017237887090715, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4481403580546466, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.06851723496815999, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.40911149660575097, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.14184998906630783, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.44498159653494584, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.098684745093626, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4007829842063641, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.12459539355692184, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4660673682008178, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.43650150602378024, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.16852726931996573, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.47700454282460186, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0967458811247473, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4485783191522753, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.14259457481008844, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.44333951056770365, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.12929801979373398, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4481163949580147, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.05089649055811939, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.332316583093035, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1215444014819075, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.47810748222746724, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.07454524508730044, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4226523751275279, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.45094066627298346, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.12140604678816087, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4867949101127361, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4257191895245898, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4447505575009147, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.06790750885658495, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.36461852531844696, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.06580605405558394, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.39253122769812004, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.34130342683703757, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.09309060319054646, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4298405489249517, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.36741937011390374, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.11220450894323894, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.46129962837218175, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1495364895327543, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.47363863746713725, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.09996446612314541, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.38170822021413087, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.06387054393436563, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3815759231072373, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.10226898445462904, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.31602168772086425, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.13308739447486365, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3932447622969156, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.15945111742363355, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3874937023246531, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.16222984538693397, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3853884541190584, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.04590350535783419, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3590907949514895, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.06553112247619124, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.34736601570005654, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.28746043870472343, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.08090780486139712, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.39801116539473197, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.13634149384842567, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.45660196324556507, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.10539949748136965, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43372525820935726, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.08313078148769443, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.37751928853187794, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.11705228389611827, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3876750316897958, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.06945941539174287, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.37532824377184637, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.0017825311942959, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.060825626903085836, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.367772007695087, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3275292968031138, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.08932983819566953, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.37462132890676997, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.12151683896637884, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3874631848880938, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.10204941450542204, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3642762802151916, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4198632525977369, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.40030811252315135, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3645369664653625, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.07197294819814848, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.32449572804662435, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0888682354086992, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.339535780138334, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2954316287998063, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.13508587062654778, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.20625143302701235, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.10744704576329998, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4113914052054571, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.061599223508298384, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.39071299620062516, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.08121271060180286, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.38347124715279823, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.346134163535414, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3120575186023678, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.12703931399200974, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.36503713996419634, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.25122591039975606, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.142144689462689, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4331731101712559, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1383193561213217, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4229717720106369, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.14846392828893068, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.44939103256256696, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.12146424147064877, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4236242053572171, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1094074965643601, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.40564547968508147, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.15220822456235364, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4115596298004114, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.37988778643556725, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.15453746478246141, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4413516563123831, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.057437241172269976, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.35678099544211456, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.054740285583782515, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3326088942846013, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.21262860902391906, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.145714476532026, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.09959979931751661, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.11584671534637218, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.43405442508386655, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.10824174794790033, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4249858140828141, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.13364464646895982, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.420485716773103, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.10642944544652122, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4272539643561774, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.09994208395394132, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4116031651908585, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.30779033808655853, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.11665236403515139, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3539070801331386, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.11340129142744679, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4168800407013454, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.07438681343481453, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3894532190798538, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.12289012856297825, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4301477375362509, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.42269142120170566, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4070049032521835, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.10713148568717314, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.41522111700393083, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.09117705217713716, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43706480660762204, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.09117705217713716, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43706480660762204, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.1585163492096374, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3944339442252199, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.29010329480545366, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.41628264791417435, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.402380136220731, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.11765941642483725, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.44984502263523063, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3814511364616612, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3783361329472209, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.31731158276047144, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2862195367689212, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.08824413655138029, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3977541835364748, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3241317524160092, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07351652222518425, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3862617013651048, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.38224927613981324, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.37754295227618245, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09789100211394652, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3998935506194311, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3292309575174233, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3702987017023586, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.15576268293490025, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.15559260728522314, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.17228284869075539, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.0008931761343336905, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.09318751734659178, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07105722763151533, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3833002336205578, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.06699965311966219, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.39535625904035426, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2594621783720232, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.37756676543137707, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.26779197752407163, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2821488741696276, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.19258818005939538, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3162255423673242, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3499024158832446, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.12587301409115934, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.43278573034203477, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.08072859763900794, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3683463348059566, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.07801862165263017, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3649626948604655, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.31673355623145183, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.30718853768673293, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.08704115681414555, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.30654218553615703, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1218935493102045, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3464538940382064, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.16140904075314855, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.11038950880611041, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.08923623051454435, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1623104334751586, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4771296526729911, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3947523667337686, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.09092206673648158, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4200146131210127, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3701108638788564, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.06534705417606954, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.36650330882957155, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.10505472012980112, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.10823255315380634, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.10849792605943348, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3961285597009415, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6148751441350505, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4923751299732868, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6853756490381199, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3996712647649035, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6353525755760105, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5115346945020283, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7037574715738644, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.539613476474223, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7656669576227642, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.44323526910431466, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7203175886481126, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.38870674200492367, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6484380084879691, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.23904922011090457, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4803366376640879, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.23904922011090457, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4803366376640879, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.24715873794308874, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.49051792813181655, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.24165618759503896, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4975964813831709, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.23904922011090457, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3399292774084129, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.24508104771894088, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5725552336126134, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.33608213382072566, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6155314069125684, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5091686102291805, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7212096271583858, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.059225812220444374, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3415915215786091, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.20801258614305904, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.26703508536995574, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.35315040956049437, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.625895188503691, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17374951565433233, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.45325597884524305, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17743299460161885, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.43071271897416463, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.16052654068024738, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.41580120868053494, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.05963579607071745, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.31139762378406344, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.16882878525950934, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4916588179493449, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.06724888422961112, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.39667480605700844, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.11133996756497437, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4410280353998367, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.11930191477839873, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.38127647898994615, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.11930191477839873, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.38127647898994615, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.11346446511593337, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3675317022605926, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1138130543686042, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.37129771776482284, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.09880177230676102, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3297638349619511, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2377604053257556, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5690390533910819, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.22573408807826306, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5444672928195973, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10742716472890976, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.42694859148910824, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19073363590503933, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.49895382941569383, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2382348118072364, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5209651952837622, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.04378394322066971, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3208878744579877, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.14745870033404418, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.475170637938921, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.26801022984888695, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5654883864995515, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.21665407194210906, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4344921442639243, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2735429726790281, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5644723203818537, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.20223322445648179, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5084057058209687, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2783519250162903, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5348467461069981, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2868985878682555, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.591501744009396, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.26459538953931094, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5272178908335121, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.21339518760946108, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.48087345520828384, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.21339518760946108, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.48087345520828384, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.012201453805310429, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.063050817196087, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.13144312778782385, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.39885548494708645, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.17546787062208544, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.26318271943814925, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.24342570806900707, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5341782261409304, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2941675978352054, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5906648119376218, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.25848476545940924, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5525933856866961, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.24071298960902482, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5438509851618877, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30181468526956173, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5742266289862643, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1524391967594511, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.40401082182864007, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2063890416514164, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.38567678850872256, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3295566054952435, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5816133441895466, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3574583793293068, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5924115119819969, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.37994652561206577, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6464467277069994, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4206507730319955, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.678851303587664, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.35367180741660353, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6344846206551544, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4583059140964007, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6572591475957218, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3428955163829333, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6023036718160529, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3563758622144919, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6037023613177924, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.23476486638430955, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4773200602980358, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.24071298960902482, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.48246317686203916, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2632018059331281, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.501302719796297, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.21190235548035158, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.42394616175486477, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2026004770366011, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.26423618098743384, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4538010737057216, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6446834621229663, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4537725564472931, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6400294742979378, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.20586736678432452, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5693016623172978, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1455399826828606, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4504825146558032, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4537725564472931, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6472259254275322, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3224480215988163, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5927918264487643, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.175866555062937, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2758687846643748, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2948978498692003, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5529453973837751, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.22292726306270316, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5653789747970112, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.09362261118571368, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3452056942265759, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.26930937054323245, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5410704185827219, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.24634765861867908, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.55968513851572, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.26639861901254025, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5645550913055297, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.29037747307996287, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5917006930610393, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2158914621804855, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5448184155666022, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.14354007514054795, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4107294810888034, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.14382854899355546, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4429424015358985, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39152357647177133, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3628970589000386, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.26380332796984857, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4054234087021839, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.667304751638097, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.0197185083394535, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.08175340974854195, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4308342322390109, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3268233487541633, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6084114123608597, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.39970543200306696, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6701057243509293, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.057855095943418054, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3713083115938122, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.04759937639788563, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2500653935141143, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.585528867886047, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.21403222128228389, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.563121432204311, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18917620656425485, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4346170232980484, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18505378795140082, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.47051087423292237, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.09807167131529582, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4646043403137081, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.17246578136934215, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4978075400551749, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.12049505059461789, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.49305039430054654, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18031307339768174, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.522164454804456, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.010790603731135676, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.08933760969291045, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.08321246411701612, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4202131284704273, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.037874984245935134, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.13083094614009624, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.07811070608237462, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.36587492277430317, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.01048349685717822, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.055565415325616714, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.30865045220428267, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.61517480898171, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2846319621273652, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6104886550509491, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.20064110494011925, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5205761630334527, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1573857459340795, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5347526444819753, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.17664836757774102, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5371605646337243, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.060180778682989704, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.29283927549819116, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.008180069062416927, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.04605877529742035, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.13904320686250593, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.47169365083525167, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4054983797456263, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6264774230839022, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.420450507904553, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6503146347305717, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.43870712112271204, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6525926696001584, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4207445490015154, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6496192656497308, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.48775137729295837, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7197897786887384, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.36781689904382464, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6454684777803729, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2999092588227898, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5505916495384416, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.24344100611585126, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4904649875193978, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.24344100611585126, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4904649875193978, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2772655014585435, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4799723286048352, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.05694565324984518, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.10703784430638943, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.1873975519857385, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.31466719188226244, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.44723347386851464, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6623509160762053, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2516768028374535, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.49572209766846287, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3471036105446511, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5663019495273462, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.40468508029421657, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6187842061799859, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.31229804316214244, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5472538279760955, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.009070964338765818, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.06852404470758497, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3212066202235163, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5836558214123343, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.20051119758906127, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5334791309401924, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.24894072982768842, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5212235893093335, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.23724642034775328, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5175129869169551, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.1849419409628554, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5067677916637257, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.31892230912492575, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5875084575724192, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.49804532928450235, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4263684749347053, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.41288994939846857, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.38356258581337616, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4228574070038002, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.36267371851477537, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0567604154331994, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.29827454153543537, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.39464291294535175, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6481030286156323, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.18856993172601796, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5742215470122527, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.11126509848873964, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4338923576538663, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.17236491061326006, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5548663878579595, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2383229027835547, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5742431738972974, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3797999858273739, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3540506408782035, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08906092883748383, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4317746285352776, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3535002370419364, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5959879218348465, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.393613605227227, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6492198447661237, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.393613605227227, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6492198447661237, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.38333108639273095, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6252821653079126, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3938668169322973, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6503960273855587, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.30783677787322206, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6417108947268295, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2562849004088193, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5767019342009202, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1708279669132677, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4638787181207799, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.19851743023355672, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.49793621556542356, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.11749734515861608, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3800781530302128, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.16925466459550803, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.32423541824465607, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44464935391849836, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.696223947326307, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.393613605227227, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.645368276087673, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.10954782904363085, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5090382887002297, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2834484329788497, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5201572704778937, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.33485170416778803, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5864709039906052, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.25109549502043527, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5187154028710355, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.006569332862878646, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.060864196135666904, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2756885721075884, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5867077870431389, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.35983766090218355, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5862251404739759, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.21147734744561483, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.41020178654369294, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.3563982585943877, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5378970484635915, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.1510722413165652, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.43592329727028295, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.32762442529164815, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5817308767051309, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2162882016096312, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5347607537943324, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2465888500427759, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5221084445696768, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.19375900698784013, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4417223478092842, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.19375900698784013, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4417223478092842, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.13240628161243978, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3347576434758551, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.14990549297172232, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3679304885604264, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.15955011685514067, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.30360440229073266, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.37081839104772296, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6563960892873841, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.43674417649448877, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6420436201302845, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.31372333533981844, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5741396495481692, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4583603882613907, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.671355324267905, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4577065720375266, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6651583454016877, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.09074542617661965, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.34743483318854457, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.10077062063331403, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.09760482860544632, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2600884210903425, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.531430106996609, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2971752224486841, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.605133664481872, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2329856851831642, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5405751250637106, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2563564295134795, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5499025328773104, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2500653935141143, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5098952451698188, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3410035628829697, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6673519558586546, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2537710754125116, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5898314098579354, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22150370805587954, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5463488388082953, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.18220310573875692, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4903627893118491, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.18220310573875692, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4903627893118491, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.14574402656519908, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4275543759804943, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.14917974712716253, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3881363329343739, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.13469741495510942, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.23441276321629778, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3319944964021059, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6676204564640195, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3410035628829697, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6673519558586546, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24750028117795922, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5894646098566614, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2687379663485886, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5826619907747026, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.33197363357608073, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6622924173503438, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.1549337617358287, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.46129538624370314, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.15897333608001968, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4496168003395693, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.15089318423122544, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4042478943311393, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2786312783602775, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4836796407825139, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.41756686236967944, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5616829345739638, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4205004825822372, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5674537639314233, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.40974323819644953, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5368112087257564, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3802176949775883, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5452668934611525, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.31664648301486426, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5144731747994161, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.39461811323775403, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5655204109921267, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2460808118695353, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.423121369921965, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24527664931927695, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4209094498428288, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.219672574669477, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.37413906702142435, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.23772058435392884, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.41428526424536166, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.18227211511988975, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3382801865692036, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4624783675017329, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6143805843064278, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3116520879159789, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.47517792402030584, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3627923367798331, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5255399246733422, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3425544777717761, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.50704305966035, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2209272285481984, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.39594412177016736, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.12870376210497989, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.22151451171035633, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.30181468526956173, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5261802780475523, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.39579112101105834, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6431490866428237, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.38189567401226293, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6154314825900052, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3436153961225413, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5954254642696512, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4339219137216798, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6338401824373191, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4867425155088891, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.694902422243332, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3842999367495742, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5816504483384909, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.25564177137418986, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.49870011615602194, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.25827391508911896, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4946279037884096, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.25827391508911896, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4946279037884096, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.27946415227589155, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4938296655037709, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.23770995610324924, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4452519937393593, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.28833961053297996, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.45958301505159854, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.546590882357469, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7387035187469114, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.42605707394192827, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6273945682408745, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.26925601229087914, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6050395148484196, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.43235877156651625, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.614485867381761, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5140564859600669, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6829131724977509, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.30179316261741523, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5734438794851154, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.012951112459987979, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.11882277038397698, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3272963527043486, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5715613564297359, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.35253338922743144, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6487975154557831, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2126707920684064, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4659908460634765, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2914880531303981, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5962886968213414, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.23944666570758283, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5106509239874657, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.3157230363707331, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6026946145401261, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2258043389079604, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.528195718512124, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.15985840708020788, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.44951053332729884, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1549337617358287, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4181663627917128, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1549337617358287, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4181663627917128, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.17920531400657588, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4522763055702811, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.09150321656179629, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.37820626664913604, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1604629854143619, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3770931135093792, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.26199400535088346, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5804827870380099, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.20533250289138671, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.49681810344665644, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.28467215304840787, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5192330975787584, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1672112091212215, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5078446328931894, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0950330051810703, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.2535554509913635, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.20378172261136207, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.48600008237332104, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.24513414885202045, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5476647609559218, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23240102389974368, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4973274282641141, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2516768028374535, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.47249781871556595, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.16105265992626083, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.404377371664668, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2920934313715234, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5778663410753718, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2573392925035755, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5328565784271402, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.27217589854489177, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5756343666825848, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12192550254402314, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3548931840142405, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12192550254402314, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3548931840142405, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15813859795767055, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.44607340294350173, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12772369606112696, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.38771162055402797, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.009832372776986684, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.06995003895819606, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.005454501428722432, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.02525205404411707, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.20533250289138671, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.45975635079501215, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3077422016953529, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5943673820353285, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3077422016953529, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5943673820353285, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.10081843650735454, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.38165410078357226, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.09564571510780719, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.1907009110214351, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.10353153556093725, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.40215410362634535, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.28653528640783255, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5053636612097852, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.17979384730979156, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4177311931467539, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2767429728676341, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.51183750216717, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3192837057100497, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4886865884781344, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3800528767347385, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5075280145138238, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3020162743522857, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5582696703142395, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.28467215304840787, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4298052820106505, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.21147734744561483, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.39365062043136434, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.21147734744561483, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.39365062043136434, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.19358934025667454, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3468163065453778, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.183668071302564, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.35345479637314337, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1286057341226582, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2808359248223786, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3800528767347385, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6363479287351667, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3295957765387521, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.625928739543479, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.24328450115124742, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.42756232255111404, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.383259260976792, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5920204217586964, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.383259260976792, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.585064022155838, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.10599453139020258, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.33428722292794555, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.19180992590551618, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3308002143045663, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.22305706065076847, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5202782711775973, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.31326946419057006, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.591171976889058, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1702602472176709, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4366640707779677, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2615659486493292, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5126931977939474, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1840585956032067, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5282240694221736, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.243584033816485, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5152157451762782, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.30679661188970503, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5967827151961556, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.15426765225005337, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.45289625960131974, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.16251572062938138, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.40123444651304624, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.22908476944452194, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.004770195810675918, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.03746566558042944, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1580553860161723, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.41159403597129257, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.20675563318176166, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3349039841689432, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6225752009608275, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3057322895905473, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5821796659763352, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.23240102389974368, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5335795368341105, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.31487248334376844, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5905881236136059, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.35994987563597164, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6548318751798113, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.158045000461378, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.40165223613435413, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.03509992242758199, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.30204473943342836, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5394635390078353, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.5294442646627652, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7281375072835307, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.933651069586263, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.9586507529693243, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.933651069586263, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.9586507529693243, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.6337520241233826, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7734740773636255, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.7096224667917136, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.8862932371217843, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.7409995286953545, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.9017022389242945, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.7096224667917136, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.8862932371217843, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.882190724997149, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.943123392401343, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.39793093873955576, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6648788692343665, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.7147882714185101, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.8408773556139596, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.3359230828063256, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.573086119969458, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.7106361351765512, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.8390104107504974, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.7770554539970614, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.9260678176630538, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.8767740197085658, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.9055624233154097, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.8627586293513119, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.8964369716535558, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.9082489095559809, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.9677853954871374, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.4162915990459618, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5970097205621886, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3816408219023713, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5784105768028126, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.39234342738825634, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5972186089812455, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.361250819353898, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6105988260114965, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.46317041049597935, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6800890174642056, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.4067505079817917, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.629072095000949, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.33713757310040376, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5731908178757754, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.24931126684773341, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.44539000137249984, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.20134984470993175, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.47593263188822477, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.011439099361283091, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.07109011153265941, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.20786721468392394, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2617811877857886, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.4840047962912239, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.706836097361849, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.18236198178601878, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4546828651423093, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.4710304492059704, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6951644805792349, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.5068325976422298, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.7027078355532212, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.24793827875738764, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4560817652765598, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.20786721468392394, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.22772581789894308, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.36463597249757107, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5937597266341832, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.25848476545940924, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4897308313348651, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.18398226639192106, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.37285010531146734, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.18116830735735984, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.378028436956142, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2539169853234758, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4294871148542432, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.4041338117274596, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5261706483072474, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2571503337178629, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.437073296721152, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.19129143021561437, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.390473445537339, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.11470856515430629, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.31103797207623773, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.11470856515430629, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.31103797207623773, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.12731505388718733, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3354785767663773, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1165747879955896, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.29596615473767834, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2055434718326777, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4145758427516506, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2541277777982055, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4083801144711196, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.24814514148154546, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5127275550938416, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2941675978352054, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5720229382661602, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1361285171343236, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2916549694940723, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0440854328121759, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.053628247089794495, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2500984051960647, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.510079353939284, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.29851690541541476, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6224209860013706, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.26958884543190903, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5631664732610485, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2503955135641583, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5411247834284307, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.26115021337737276, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5520240492306279, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.27837899330129656, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5673065268668616, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.37856950851858595, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6309392505592764, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.27057949011516347, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5644281635271426, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.14361580529268292, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.38179088353033064, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.14361580529268292, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.38179088353033064, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.1676495122493199, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.36959105080753546, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2297132059983132, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4379547539491647, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.1839576031944879, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2651734406129379, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.37416241283362434, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6754691163599457, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3556383209223338, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6120361598575286, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.19300403619224038, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.572822450824776, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2799103318440567, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6172633503183605, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3888403695409309, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6733543865794972, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.03223351941652736, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2249430587095686, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.15492402556203205, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3125746694462918, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.23233851806966574, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5357993047462365, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.29796912700911177, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5158892363484622, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4005296397635166, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6201785376974677, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4005296397635166, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.591086403119955, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3114493863658917, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5682352098535879, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.27824533355692294, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5540161525695098, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.21815383167015925, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.46829275965930944, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.24285172240675165, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4655392375590772, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.24527664931927695, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4846287820466136, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.24527664931927695, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4846287820466136, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.008072417039197614, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.06388295238713035, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.013616214739412552, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.0583054295241246, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.010659396622169299, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.06195563757831697, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5091686102291805, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7320513799881168, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3297870801503319, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5720518025066121, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.19851743023355672, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.547468247371695, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.341534333789316, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5541872808406454, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4024358402935841, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6233256624828218, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.15222275337751698, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4114953475207692, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.12031041493621579, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2540681992986826, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.21910942711629067, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4572726847360035, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.17377261603583774, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4342710497791623, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.15956483578595942, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.425693420655628, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.09791579531860735, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40432986440529917, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10423563468216913, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.34390006822858976, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.17513129766126637, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.47773919189902136, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.12211781276995526, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4347129560595505, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.07276375309803214, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.38861839385008856, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.14651860136741404, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3998401696111528, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.12217872405854398, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3801321934310697, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.11125382292406938, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.36362589237918785, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.05786688295409777, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3224621533587573, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.11912074202372534, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2825717159828524, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.24759502840925565, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5238368454821934, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.25797824300060007, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5649286213774056, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.16285656455323885, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.41845720590580077, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.1752818941059842, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4632619281274353, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22659733169841595, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5133896303093581, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.07198169585307328, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.34476508589802557, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.06150895863726817, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.20484322521277584, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4996688420059074, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33631398011857205, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6332428715049205, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2323385180696658, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5019509292309764, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.19726472415983368, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5084335265908847, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.22897967367089514, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5158963534678644, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3061554451423933, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6130035189889428, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.23782678885662012, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.551668684772089, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.35205535634937346, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5769772651090223, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.20310341961604592, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.42469202210051515, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.21910942711629067, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.41756166197217914, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.196046355324564, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.43350415347352517, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1927168036916521, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4181794106251381, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1998527160015335, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.31962498795801614, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.42962975172642387, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6526674280609184, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.411677998679592, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6679764037281967, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.19057582910221915, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.44257167922089413, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2799506947952143, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5700777642587023, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2799506947952143, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5714878050026524, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1958641343177127, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.42370679353391144, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2904194745959351, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5399262338172586, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2453238227047589, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.55017080577881, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.22952177306405494, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5279520952576137, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2950615456579434, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5675143775417766, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.18643403650822063, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5048280010205698, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3466720379073123, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6312259441479694, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2363347557282754, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5588648358676678, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.21108332811806296, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5847750744232335, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1490671937611913, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4338972266367216, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1490671937611913, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4338972266367216, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1543252261021413, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3797469086855575, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1649662542496744, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4276666255930192, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1409879074813521, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.31162348789027916, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.27217589854489177, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5875203796536156, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.16617179744038174, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.48117026601244495, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23584494013034235, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5389135951883217, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3317416308285443, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6310870941590575, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1606777496729309, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5196854930551574, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.011961593826815614, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.10171812934151993, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.27271804425850804, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6231583014699292, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2063529291350913, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.41364248023079064, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3618488169166299, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5708179622131996, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.44536846829231563, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.626601305779226, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.45286243450930924, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5635810887606836, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.35484390943924515, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6152611695652526, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.30829953663635573, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5552978544646301, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3520774812078196, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5735788202105873, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.24664751641319077, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.49266142807316493, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.24715873794308874, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4876485132692386, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2336554865490948, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.38695981569355575, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.23374260773620212, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4481831080646353, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.20644156444875764, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.2756944940230347, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3563758622144919, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6152190692949244, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3602927398528427, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6148633329091892, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.20241924705494113, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4785445547362629, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3291745670182042, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5666889547785301, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3561691349239915, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5927193326481119, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.269865498431692, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4414378099856194, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2026004770366011, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.30270818881631195, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.27353798204430885, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4703704190720731, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.10586140133972588, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4674053477944039, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1712766252338756, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5225554962608486, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1549337617358287, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.47063780888858964, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.087593103737711, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.41197148322773003, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.24517917828823954, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5630094449221897, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.236963478377094, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5659243374651276, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1506914981676572, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49409850038698094, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.13731102930446024, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4144705269436304, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.13731102930446024, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4144705269436304, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.09993298280365949, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.48180385986334856, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.11846592694382017, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3317492265355767, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.09716516292186668, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.27400718580798855, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.016381257887983454, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.0197185083394535, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.11760297043792217, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5037771891801089, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.31178681104808115, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6235184561135673, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.39029400374523116, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6594442432367803, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1028840244182704, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3793737661689232, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.0054987473538930624, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.18502495276209577, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49774903659564634, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2703645496410475, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5129310433304475, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2709079038456153, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.447458019441992, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.27075075499555246, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5079958750910802, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.19134492872562123, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4261251088174477, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.28450701980252824, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5183351563352739, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2772655014585435, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5163486940590201, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2797290030028961, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5092945860838002, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.17938074771051948, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.37004164663464306, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.18380806980705947, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.37732671671330364, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.043167422631559454, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.14513634182269314, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1511810638395761, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.38240796284180606, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.1623128779243406, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.005454501428722432, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.02525205404411707, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.24420961057522048, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.529409842751342, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.20787389114353938, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5395612843354369, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.19107912313367556, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.47457026427329674, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2482239530137079, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5350941461126912, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.06104408840180951, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2770877905448079, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.18227211511988975, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.26739926509879147, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2244921781886412, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.48547869147117434, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2492031334256811, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4923163374806021, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2907608105126149, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5445465034944268, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.30219157030008637, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5492288689573782, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2166046272179384, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5246154268333804, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4173623671609102, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.653946816582661, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.34324291276089697, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6000833980598983, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.26036802768146033, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5255752089611478, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1545474372263506, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4385517123611144, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.12611435407515667, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.416865407084071, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.17714787947168362, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4959629506636555, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.15979493106715062, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.39705750344710744, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.11805334969075956, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.29355162288859277, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4427450627622687, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5831413075310591, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4980380502241239, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.716927044471585, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.24793827875738764, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5551406879143232, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.5143871785925975, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7463887744436826, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3817026511181546, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6579835999035872, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.09375485531078004, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.38990742377079385, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1568616676699092, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3333409033359294, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2256379391347521, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4863283179636851, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.43104504141832617, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5953439401847398, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.27907188689389983, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5093017176589221, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2276330877377012, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43289197888514347, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.28652679283739385, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4341260827393413, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.29512789240986326, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.490746523794099, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2425369392285065, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.46048415870417647, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.240340920378981, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4624667456597986, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.06452288310243297, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.1340641152212824, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.06452288310243297, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.1340641152212824, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.21815383167015925, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.37444773636111656, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.12729992303943352, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.34123483868512156, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2339053691840767, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.34360669379010167, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.33366586275504884, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.597451728834618, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3239689744606511, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5878660875539871, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.22991579208155866, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4195683527550329, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3529455532976322, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5455305267266531, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.35730397938750963, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5470354051417882, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.09777262451497228, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3252901824093446, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2119156724475127, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.37835612878198044, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.23150355132919254, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.48517162463112556, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20863984464930022, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.45879801940552783, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2695149221768555, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4713033964653895, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.08839914053546608, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.13210046935115544, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.22669629371608005, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4780713176952279, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3497701087305086, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5444479222621443, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.321796895215673, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5555275088172927, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.35592474790742606, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5565115125775245, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.18553468405289997, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3940963548952763, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.19049091104611224, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.40060792914131615, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2062051322624683, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.41192098101671093, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.18379651914635886, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.36124868671762816, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.016680172518945505, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.049377315765891015, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.38565864734759825, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6607139809585929, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2505547110465864, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.48036570052288885, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.37294595046144213, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.598127662881266, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.35451444797329384, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5965971449645624, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15146825617322526, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.33785686884467514, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0034593773364647584, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.10587910341470286, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3295957765387521, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5207914581240252, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.27338789256007584, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5429269981031598, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2075953797357176, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4344742362498603, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.293816771214877, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4842449940538771, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2063529291350913, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.48123766976272336, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.41737386808061633, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6106512856048538, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3268233487541633, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5342805780357801, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.27075075499555246, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5201548999535662, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2306483512507339, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.45504570030979885, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.23095037282123296, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.39553614028855416, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.11546772122737221, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2604812246395473, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.09815096202645017, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.08571854412510894, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1334566096462065, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.25537293849808335, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.4175984139783788, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6502955433874209, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.26709890828869226, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5611797797204635, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3658141331541051, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6386889736882309, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3748533897614559, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6415822793896023, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.17001078098404232, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.401579352670784, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.07964662206989197, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.08209382469898788, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.24759502840925565, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5330580248133261, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3703971546860334, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6509854048597393, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3020089249326176, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5666791239956741, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3169340575963432, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6047772126282382, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2728224724839342, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5858336859170117, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3468503425098983, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6177731406412544, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.273568639390329, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5735412935013542, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2666372228396489, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5839132669613946, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1676495122493199, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4477014617496043, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.17893757508901514, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4768883480817015, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1649662542496744, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.44732894301721, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.19049091104611224, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.442891478328311, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.19834976253918618, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.41909810865014857, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.005449161724399305, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.026158029267484995, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.20812209921683228, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4762583476044399, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.30140436874237964, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6234338871585586, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.38002588146683836, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6549174592735642, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.26004850047646383, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5795275012848826, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.13582344277578873, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.23233050093887114, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.27045803893058445, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5815404493073867, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1515551103099189, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.49455791760408774, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1059786102229136, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2561557976916047, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.15507100728722165, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.48322409198286276, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.14889095388455822, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.41536400762130277, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.3800528767347385, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5867504754619237, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.3057322895905473, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5337455378139571, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2667836062177809, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4889374373828587, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.12869567424741998, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2959351858751658, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.12870376210497989, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2961496632884161, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.12486557620383446, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2904789102327634, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1059786102229136, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2561557976916047, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.10908370302374089, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.24648500279736443, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.36644357745505135, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6024962574387346, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2934447092159934, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6498290192480378, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.13551668809076822, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4424571214083723, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2697482929758505, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6331597127209819, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.33047557311918846, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6190675011020178, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.05327003793015713, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.23036636097561497, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.10369816700638204, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2527691069954848, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.11930191477839873, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.26295403442210813, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.24664751641319077, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.48702383483350364, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2103019561790119, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4375454771782611, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.21396075329540654, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5173735729399421, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.22941797870527758, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.42186981875418683, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.32687808175061417, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5888362088090499, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3845928641813324, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6331548374111277, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.23919877618601593, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5302876334280949, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1992314067597761, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.38794562922191417, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.20711840252285554, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4418611388914859, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1465911128169728, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3079988190146739, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17935599848863806, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3590687067479934, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1069893156459595, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.21361888501132265, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.37042346597404774, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6504303479968405, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.24527664931927695, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5385267265433172, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2736255491551285, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5566377410597074, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2940297877008057, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.542815022290297, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.28847676899197566, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.49694236091528354, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1509387354925112, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.26939418948215393, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.06203726059862019, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.06824072321166202, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2119156724475127, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.48896874501469645, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7281051247089317, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7882997401328445, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5806197937310393, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7346706700987636, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5793367580502561, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6502428441722727, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4855332614117322, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5299556742893647, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5411953360894813, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6689891795277099, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.369345079296433, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4718547623527638, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.38249626297768063, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.40976234193505356, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1477219991186121, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3092919092976881, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3387562718376491, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4478559739568199, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.369345079296433, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5103516764863386, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.41558132327975467, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4704204244154549, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.2423441824135159, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4429509373913047, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4646232199104102, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5678926447384061, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.6064630666233242, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6752055521830945, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5357110024227318, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6365941772753647, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.6960917409740967, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.8209757784637755, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7329410355605002, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.8468261925085733, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15371371932217712, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3322937199755749, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.14790264259417688, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.27159767590045303, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4751132438608344, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6849386986272349, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.25552199116069907, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3799133205289109, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.23386786214190372, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3682311523733465, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.11739521786077453, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.22090491782919655, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1892240568795935, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.280413108453108, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.09960206740894453, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.21445174594619118, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.13857814312261593, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.26136391784313634, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.08635800047213174, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.218109371254876, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.19794179570942658, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.19794179570942658, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.139800134566647, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2510112235832054, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.34791594751284466, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.36381439222876993, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.20233074088759792, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3746629492952356, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1767874865365185, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.31807700660641347, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.37284875432797243, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.44888401040760956, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0925329498915617, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2110486160692096, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2887308472548599, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.41654484827391225, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2971085373234417, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.41681011390626077, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.1907589726146516, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.12453389344594705, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.141543757252386, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2594145364221844, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4093301993048525, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.512762518189388, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6244631487487835, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6931369519059803, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.581972638479957, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6970914528585833, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.44120063733294235, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5296624608564717, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5411953360894813, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6689891795277099, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4272870063962341, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5425603129070803, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5642761727828352, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6181373706707737, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6458552885189878, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7468283944111381, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6458552885189878, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7468283944111381, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4440750605884706, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5402588602256685, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5354063183898494, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5965096072299958, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.44120063733294235, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5905813392824112, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6242817472465665, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6834390596430621, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.7329410355605002, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8247196817311783, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6458552885189878, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7468283944111381, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43310177167002284, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.534533410927948, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4440750605884706, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5402588602256685, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5411953360894813, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6208023495269347, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.26481979271706185, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3212854967972961, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.47171327621770304, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4577275269488853, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6747054474171109, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.25383339228798274, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.45896379476820603, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3508739523842563, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5533976153694653, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.23705266435224473, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.44716007458096513, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.33150414660895594, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5307991156599932, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.27046570133003095, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3736509638751225, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2615858282579583, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.35447530946908884, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.17878540236558915, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.36568234925753484, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.17878540236558915, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.36568234925753484, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.25530635525095574, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4224404198283467, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.34674958774339726, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4348853298961402, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2964215118800292, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4213813461128635, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.30147856626075187, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4883780556286986, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.5805399561362194, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6599074620651243, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44392090655418587, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5678926447384061, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.40891568776497583, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.46522329223142805, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.7329410355605002, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.8468261925085733, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.14793378747473623, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.28942235562470353, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.11436433361427001, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.23221971735799607, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.18580985894574314, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3347249292100999, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.27668736912821895, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4414406760568898, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.17200767571780612, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3723150838362789, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2465659486053858, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5689069160047179, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.30391153783979835, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.15481575551900897, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3242496687697624, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.12887696534828325, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.30114368429557287, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.15138514598766048, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3237497764315872, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18012107375362474, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3031860269594791, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18693000799960027, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.29214034034017544, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.1544458227548897, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3343587266874694, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.29160060199573634, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.611038619206726, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.17080052973495516, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.41295134318620164, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.43310177167002284, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6107152353968289, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.16369773101364, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3525432121056259, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.23817261442630488, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.448286611717823, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.20679845323803403, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.47636494608150104, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.196046355324564, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4861187554848482, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.14380553624999498, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.2597661791838868, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.09147827112247602, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3258762519783793, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4751132438608344, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6159319815107203, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1477219991186121, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.28685201698226354, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1477219991186121, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2391308148553106, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18180608220159192, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.27307753334479423, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14965975078050625, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.22213502776474325, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14965975078050625, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.22213502776474325, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.15604242268653643, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2255928425212252, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14068535649874328, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.22369939407063077, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14643937864373885, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.22808564446823346, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14965975078050625, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.22213502776474325, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14965975078050625, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.22213502776474325, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.24099646203241393, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.40842567407749947, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.49897421349092935, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18180608220159192, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2765353481682209, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3160946016179871, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.407876439044591, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.17466240109087192, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2719194508460068, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.15980518115118317, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2292736049463283, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.12316365460790003, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2615858282579583, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.35862918415512257, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.7281051247089317, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.78479833664205, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3254455687469726, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4474512036484817, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3267294026204632, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4510525482602028, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4855332614117322, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6448214024803467, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.21690365808279138, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.33065826652002533, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.24728515687112834, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3088155734423375, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.21333164424828907, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.33911412792045653, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.11391856953132565, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.2717713021928714, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.27718461611705486, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4578226095312774, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5187171262420485, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.19895913918781652, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.38716933464075676, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.6052987576779449, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6657086815551626, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.5365920629514802, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6274039030337838, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4578226095312774, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5406295999835291, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.6676191940689508, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.8138710990447064, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.18029268617744973, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.002054231717337716, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.12286996020967837, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.31567668741706395, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4815092081725061, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5820265218174012, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.23887527917609022, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4120359948636439, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.36210097004176117, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.408098151133905, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3165014630070639, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.42516173623967946, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.36923778753333203, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5093945382661453, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3685289119518548, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.47062358557598893, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.353203510510529, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4910213297498164, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2042128370387497, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3132427423570805, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2001670147593021, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3176647235897937, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.15820362165931962, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.2249046365436241, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.369345079296433, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4918148373059308, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.46181382506716123, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5392962545975036, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4185938787651429, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6016367461945803, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4192761856401719, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6279656551060881, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4753167451887016, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6372909532389948, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.38317923930200504, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.47975624978837655, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.5426924329239604, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.578377079605085, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.16341242314728613, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.30086466715081783, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.2054194471318506, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.25678404806291744, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.37045149029437513, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7246473808162345, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.728208634600343, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5793367580502561, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6502428441722727, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1243018504102695, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.32950116238735283, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5198707241967666, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6498183531322053, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.20664181816537014, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.371359687688326, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.23660362391696813, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.34152697838249696, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1477219991186121, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3092919092976881, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1477219991186121, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3092919092976881, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.369345079296433, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5103516764863386, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4587032440161705, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5232464635424798, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.23603721040376854, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4074433070802772, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.6052987576779449, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6657086815551626, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5357110024227318, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6365941772753647, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.36763082847636347, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.45637140510576385, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.6960917409740967, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.8209757784637755, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2651756541673285, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.16935976352352106, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.31268514922728713, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.41990725085948355, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4388504279172877, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.808070563320424, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4841156774078945, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8256726071164937, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8363600587440573, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9912737182609732, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8895260356363631, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9215559912711291, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.6018154975998465, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7669980679050217, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.47320724783393625, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5833006006517599, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3556521383601747, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.594830811413066, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.5406964703993759, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5964595329953364, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2575863752355164, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3717184743596148, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.13585813340607317, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3021348975068449, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22481074167380632, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3761108267186685, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.34589895849033114, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.44792042673107413, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.14397786194708656, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3331521962085306, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.14587521254752497, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3305597683917539, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.08197539732074254, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.2552663483401067, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.33018775735516415, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5054531554717974, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.15146316523107298, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4192400624404484, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3032929624979452, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5077415447889289, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.43994654743790196, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5758276578902723, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3730786950813075, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.47401660085208147, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.38223593598574, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5729676575997464, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.38223593598574, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5686739421910859, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.21711852081087685, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.34076978472998576, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.19328966457045355, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.20477156411200437, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3371728179865314, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08939270118279458, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2952752522340665, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21629114799587432, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3542320138389837, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21993356630819796, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3822901360655399, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.12212865548711085, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.27604929504751197, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.15804606946648236, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.24864035916056065, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.007934677500708292, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.19984607356962125, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.29326031481052006, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2674274417945491, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.29066274199907366, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08939270118279458, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2952752522340665, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.1307118752097732, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2556075727355655, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.19545984328607466, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3260504123048448, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.17729842264695017, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3337514618651578, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.16341242314728613, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.30227683871289934, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.17095864413061523, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2805749649536233, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.13952118378975725, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2962794525145751, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.1307118752097732, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2771420974564079, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.1907005287801752, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.028735632183908046, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.17670087745185423, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3136010782144669, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7246473808162345, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.728208634600343, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5793367580502561, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6502428441722727, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.17662903260733673, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.359573626731952, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.30826423742301434, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4128975675984797, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.13502367316243039, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.299859745321103, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.27274191069381915, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.37436438971100644, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1333497993210919, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2559597722970139, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1333497993210919, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2559597722970139, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.526589137558171, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5667866238125795, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.17981949418962662, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3488441223298029, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.17857033414091059, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.32632435359302164, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5805399561362194, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6599074620651243, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.6244631487487835, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7155411017347171, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.6960917409740967, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.8209757784637755, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.43070794242402144, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5011615373298621, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.19665864691817672, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.36913377112413776, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.019516573752972968, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.22419056820298167, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3577306040313533, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.583526016818016, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6994652193905146, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.27405612859390877, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4639958592456083, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4390960897971484, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.541742178821102, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.13232291594986312, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.301901669683193, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.268250341087026, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.37630621020765986, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.3166144686275811, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4171828599209745, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2434330428491034, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.31858900384957733, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.25430316746203985, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4159778448357134, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.25381494737245897, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4177779282578606, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.15084825228964133, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3284886849880412, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1508920852219557, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.32281122236013104, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.28855357268630083, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.44235337548914555, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.3160946016179871, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4791760084407935, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4452652851854937, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5889782977654896, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2677353447271197, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3932141708916282, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.27326653732219497, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4001542443022677, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.23359433863044574, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.36161782617294214, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1536690667279411, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.23373462830676886, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.16800102974369996, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3319781987745275, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.6052987576779449, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.643602170728296, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.13004800471424346, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.28217142159025543, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3924259174695316, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.45050557152077386, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.10601317434781207, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2344095627038401, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15450079547146164, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.25100896225203706, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.248781805015534, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.24007528246707907, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.31084467045503017, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12416659058610632, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.23141028782228498, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12416659058610632, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.23141028782228498, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12769027061800275, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.21844360831325868, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.26853783353673283, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.41566337942217346, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.16599711114472157, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4246183605185108, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5497460511936695, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.22523697594538705, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3911595396314754, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23705266435224473, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3838188339168412, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1852972751417938, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.36660412101424933, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.16341242314728613, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.33893747430370086, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2469646873408414, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2653698485201136, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.4815092081725061, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5785251190053333, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.37821486365532614, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4718665834023439, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.35423985843000033, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4293667924436175, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2933705789311311, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.35570110758127277, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.41558132327975467, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4683680115570169, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3730786950813075, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4080871920416184, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3674668904964848, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.40975628086142124, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4104273001940124, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4104273001940124, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3931807596037881, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.41587358041151196, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.41546060026113085, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.46431680824298277, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.22128776529156546, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3299817815368062, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.45167594566243024, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6430302720642738, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.4578226095312774, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5429809487027987, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.17679588126795498, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4098986063548376, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3675058901988579, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.445171638403697, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3811228251371368, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.45807534399944205, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.25567957494892185, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3431135836501165, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3196352513221046, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.29107087297820256, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.39517833279310743, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.38694317759010316, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.45827711860455167, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3699382260470039, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4032851361478274, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.42378190548671596, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.47335507275218824, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3763278728427448, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.39009457811977266, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.409211292187266, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.44521767975773685, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.409211292187266, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.462803416015263, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3763743474188506, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4120099199050514, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.39989254486815534, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.39989254486815534, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.34791594751284466, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.40864368085475805, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4093301993048525, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.44717887287377617, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.21271275367465078, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.29643115550453636, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.45267625566586717, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6356631092098544, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.45167594566243024, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5192073147540899, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4056782022243561, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5237454577692897, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.409211292187266, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.44289452305459603, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4245970617334277, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4579580788935747, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.27334594211112967, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.34926643308225325, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.139781837804502, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2134385691462796, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.296993231533869, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4115167991342047, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5649900101054287, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.45167594566243024, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5169677927619225, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2706805630983137, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.38186806613291924, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1890425467840326, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3513019690066663, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.22455129433835885, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3153073204562459, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.20690996611611379, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.30036193380302606, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.23270804908165135, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3478589640284733, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1925775824064372, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3523071217485035, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1925775824064372, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3523071217485035, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.11234905986715489, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.15225251521949978, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.22534921437308478, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.30558055644143256, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.13461801293778908, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.32028794303934305, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.38694317759010316, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4758624095139857, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.13733894353973466, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.26356016327430454, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.15878174295086994, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3163237075880393, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.22095731396358687, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.33443277609714755, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2113573874732524, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.014379215591354156, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.12943648490176665, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.29942831535046555, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.24489516889906388, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.409369762090413, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.23386786214190372, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3780009826926042, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.26696378876165927, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3581548569027847, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1262744724314408, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.25266688865379994, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3595597536132021, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5042608116537557, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1961887304255141, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31368406470821447, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.22453002699007485, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3354597455808525, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1491744505572466, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.23672011749048205, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1491744505572466, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.23672011749048205, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12061450720815534, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.28227862122593256, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2448987533565238, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.21936644511443132, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3266422289425898, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.702540870003671, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3011172971082868, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3734627919313833, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.26518122980477765, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.514846875413034, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2082376263771737, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3665582908776792, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3159148237572417, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5258141913574198, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.0034435261707988977, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.010917030567685585, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.22316698150381944, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3989952325675248, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3925121365052661, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.47788592802001717, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.35423985843000033, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4401068255722377, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.19263684669277223, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.16368118043487417, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3476956163805434, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2187746652191371, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.18341524527739528, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.14567343886386178, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.15703032248735793, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3020103087706165, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.36625663694634303, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3185739648783928, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.42685007822661736, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.26234693671182024, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.4772894233335957, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6272300080155604, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2852650068463884, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.472092904441211, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2523841428380167, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.11146727460890443, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.23969027175152666, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.14100024578768863, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.33713039237182474, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.1820475071426938, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.1123102665458642, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.17729842264695017, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.32305168353427943, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.15896519992112562, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.29513999460654694, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.1423412184218882, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2596718628394258, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.17615962296513688, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.24431474547499252, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3120848453730729, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3640187353243162, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.11856660123276004, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.22066843647070425, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.12789533377801793, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2283763803651714, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.10511846841633776, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.20849775250910704, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.10511846841633776, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.20849775250910704, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.13502367316243039, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2597905925100196, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.13834368456410945, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2622351749057803, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.17334819740046747, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.434975077577922, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.44927463951082325, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.16805936904720342, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3269489741572828, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.16279348731624776, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3149639290246331, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.28200049157537727, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.40682121687319617, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.28200049157537727, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3809375829720542, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.20069190971412876, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.12409597120849801, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.19449255248446348, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3571150500823898, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5018967494794737, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3572188192648703, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.45381175288762937, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3572188192648703, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.42937064888927773, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2513073726775429, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3798674638470122, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2677353447271197, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3576865471454043, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28089241320678904, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.39241665461937186, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3571150500823898, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.44642876819396304, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3359540718229689, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4335064729510061, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3926492355497174, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4617232533456601, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.27274191069381915, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.39756349135906077, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.25381494737245897, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3194196588930621, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.37590194925806086, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4642775123967649, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4470252726010778, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5551045432161744, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.25951859031182145, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.34406582181104034, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.13232291594986312, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3103406767609728, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2295748846661433, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3277581848986239, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.27334594211112967, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4045014812005364, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.11902001907030836, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2714975491916872, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.19040700845445938, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.354176495487078, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10682827247639556, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.21551117313912851, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.07425055521504613, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.18122341046764998, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.16352670859125373, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.26406333983187025, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.14974959199825547, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10640850690356463, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.1954606751850304, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.1022875701616399, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.222885061328114, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.08968235248346597, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2175311081388801, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.07174630278990472, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.17633434609960705, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.06695900686562914, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.17180011357991665, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10640850690356463, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.152668380659781, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.17259582659449696, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.09918661835916037, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10601317434781207, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2251385457970532, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.16330657473945515, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.33688142820108186, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.09812163258584553, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.23909785111906673, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10401577613691954, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.16184347717072042, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10601317434781207, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2305932305892788, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10851354579652327, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.1503151900202639, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.006827911047017742, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2164910348876327, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2774527633525211, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4358323759361012, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1978585723043446, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3527599187160617, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3021375397356768, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.460354013765958, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.12991916506579942, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.27889392608860697, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.10765326248076237, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.2268211743213014, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1029370476768733, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.25083473307234855, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1472462377094902, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.30525310195831357, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.10682827247639556, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.18978045999305448, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.09941490945601678, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.22897188670060376, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1959280139287724, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.36708131749832384, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.36343365059404575, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.432454547955832, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.15326741815269776, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.31415720375698164, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.5805399561362194, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6804343591858393, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.13796620851017113, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3011443479254443, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3166144686275811, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.39315143982598805, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3761648431086742, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5466736282576272, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2910873658777246, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.40017491309543407, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.10884267615693713, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.24899186333705978, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.26007925058007886, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.5199302229930708, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6017481019884499, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2523019529343173, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4406369072888057, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4195959935514934, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5643628666004862, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.35974578964005544, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5294218015563622, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2934521273973611, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4075394810720701, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2616747576701774, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.39134557450212215, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.31314224813827346, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3932583887521134, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2921936290725188, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.43767787354013643, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2921936290725188, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.43767787354013643, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4838257582776513, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4501609222100726, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5565610322131652, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4315505266952602, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4766479849266233, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4671778989333441, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.583541922992295, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.44411712310948115, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5742558726077623, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4671778989333441, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5801543735794272, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4501609222100726, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5779114321769039, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4501609222100726, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5779114321769039, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2633684431598725, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4212549338281654, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.06170484898727104, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.27199778234956107, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4129085501138227, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.19230188007838597, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3407021378942239, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.41072675483179805, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5635589150380774, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4122974402951816, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.49812945858788304, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.09812163258584553, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.2826014149329834, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.29486296661855094, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.37572427578597467, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2637873055942232, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.30768668074852223, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.24728515687112834, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.31221693968406194, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2042128370387497, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.35890293750629537, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2042128370387497, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.35890293750629537, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.16954555291875742, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.31800856700824265, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.21004850229269242, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.2695278236063314, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.24328221242512443, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3587841404695592, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.6052987576779449, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6657086815551626, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.6064630666233242, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6752055521830945, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.41489895705463226, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5351666707169298, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2505523539251516, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3831975160557709, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.23244223633311675, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.35864519940131245, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.09694361543655163, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.2353989148941136, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.03616809285846403, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.19004145843928574, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3699750032227405, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6612342258381259, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3883375900135818, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4643731845106876, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.11556647985416685, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.23748323325414847, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2589451141492935, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.36265302427150575, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1157064510816097, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.24091233899862727, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.18432769897186205, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.12045422179467957, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.22184013352319704, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1143433820088083, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.20225927443573538, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1494197912720898, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2347938067180855, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.21223633441554032, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.31520576641768766, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.385934808400546, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.38257849677977857, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.11563084454999199, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.24178063211164538, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3925121365052661, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.49647175863031867, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.17846877279661646, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.28232267884836304, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1532685994792829, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2563896884841204, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.25957530464210776, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1691896235111172, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30689082834840276, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.18223058800557917, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.6064630666233242, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6712747226800536, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.6242817472465665, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7123666275414222, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6560788161152474, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.25841450487427714, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.44494784218322847, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.22743363869750483, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.41347079879706106, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3360020594873999, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4979723869498355, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.33062429129755794, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4887128900317842, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2951516238086372, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.40065144019204096, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2830789070123405, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4006557494747156, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.18279744869146425, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4024804882630303, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4461240556373289, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6245673099524237, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.10050942388421231, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.42988105429544615, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5765642529796587, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.49764480798089855, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6328520698047967, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3360020594873999, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4979723869498355, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2676032275663791, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.40689458580141896, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3839162951943952, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5154389469360604, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3307203628924353, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.49086425308764237, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.22319449652482443, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.233078149078302, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.41167690646865734, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.14728954312449322, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2256490809237466, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.37300331821940047, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.24883108274644028, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3329995141432608, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.13827175716697776, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.25880112791050663, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.12219667481477892, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2405164296456886, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.1316478146760647, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.13536681105774234, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.23595972523293418, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.07939087147543496, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.11006637454907114, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.07939087147543496, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.11006637454907114, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.11856660123276004, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.21303170584506914, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.1649415532676442, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.09865498818536263, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4027788021844848, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5140425250930961, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2536955091952947, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.44037464621764255, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.26505211456170086, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3924854246504529, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1601125708485386, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.23752778281494039, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1437791910008819, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2548981391955141, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.1200550027704878, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.033908919446183204, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.15843589640881697, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.7795149903947967, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.8912732146280626, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.6230832293767097, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6994652193905146, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.36763082847636347, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4293667924436175, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.43728553857900826, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43806460289276367, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3535749730730369, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.40456707763346417, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.40635491179072764, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.34791594751284466, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4062384532979022, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.39969214713924245, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43942997265104256, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.39969214713924245, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43942997265104256, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.41546060026113085, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4663335536810786, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4390960897971484, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5164819146651056, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4525447568689241, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6016367461945803, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4246183605185108, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5045638981564646, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4578226095312774, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5429809487027987, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4390960897971484, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5164819146651056, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.409211292187266, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.39189287710585047, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.27748702735605824, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.371892873556356, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1600733593956426, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2350173429055301, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.27182269429130823, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3135936384682831, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.30389058699653954, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4310896909809194, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3763278728427448, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4261526683335186, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.36210097004176117, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4423339372603474, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3763278728427448, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4047854120649662, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.38656953855321047, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3844238861690475, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3917196589390866, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3964644743683115, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.33737554588923646, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.369875665962309, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1423412184218882, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.31142792394410035, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1863161938392376, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.36138028769379077, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3780488661667278, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.38749538363085073, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3780488661667278, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.38749538363085073, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3040122368256446, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3640142383589547, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.443579034212419, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.48854522816542867, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.443579034212419, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.48854522816542867, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.4246183605185108, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.501948957312799, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.32001589569502475, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.41050505670086324, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.32522111306534696, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3743770394908015, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1767445234920605, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.30304368225621264, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.21163700429456012, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2754475815887392, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.25437706194445847, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.28858721839661267, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.39022736644855677, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5202587069271436, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3672404084841361, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4518744271362045, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.34332704063408953, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.408639131209588, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3672404084841361, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.43288682804187184, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3924259174695316, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4246539836622663, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.34791594751284466, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.39981345815021024, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3924259174695316, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4246539836622663, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.21448629472025388, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3142841653684826, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.21448629472025388, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.31086886046532736, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3120848453730729, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3705328519354151, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.38656953855321047, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3880470780323705, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20477156411200437, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.30216175609979257, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2082633426637247, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.43955021643262504, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.4185938787651429, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.49815219590152665, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.18059154473936082, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3333808784117231, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.27334594211112967, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.35690726265980793, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.41546060026113085, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4397124902714759, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.27326653732219497, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3528072458588813, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.31277600813200596, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3423771857129358, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.25944320225692963, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3049825437064534, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.25383339228798274, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.46123461430035645, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.16401798649868696, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3760928911869727, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31756348590173983, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.612638372401986, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1535259783865636, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.35449697447586703, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.23966219681055514, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5164809275250435, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.13750902305262408, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3476437557836216, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.21027545940631823, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4572185175571455, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.09812163258584553, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2684447524373158, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.09500266321476487, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2717648186978408, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.14113991930789777, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.33851813032056655, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1462806365365753, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3207408262155079, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2560038657424253, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.5204944454433559, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6659376403204792, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.5040802179792181, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6292677087296895, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.25383339228798274, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.46285845798510755, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.307137308263447, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6108807661013372, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31756348590173983, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.612638372401986, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.22797131720811048, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.104552581027927, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.22766480821275292, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2140405179077785, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.17807129401511626, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07843772989359644, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2669076052967215, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.12913533075470382, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.25219595014343127, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.108043996762779, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.24726477214045167, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.22018448209829633, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2705349647587311, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.08635800047213174, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.23875573724774168, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.11414633188690328, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2503197875391322, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.16156345887749107, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3073644007222291, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.16156345887749107, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3073644007222291, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07418182487612639, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.26363958328353637, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.11450137919698138, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.23075195332816217, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.24822495192832897, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.31986636367127785, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.15082713742973322, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2362536212361225, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.24671763489589052, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.31806081798541963, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1022763758993479, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2461976716440084, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.11092770141728163, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.24752626772001793, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.10788569011528462, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.24852458431667404, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1770481008376135, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1179949261549654, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.108043996762779, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2560670416470495, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3029928206533524, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.45262153733641225, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.43000007605628365, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5073076708050636, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4125656013737127, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4621663225660634, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3512502252598613, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.43869157736529, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17414675099971177, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.28584149811217957, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17268932789342512, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.2845292485005295, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.18105048502088059, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.271054087912132, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.14908960803395838, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1969983001676391, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.14908960803395838, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1969983001676391, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.10991514729498916, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.2549321593272589, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.18130004952029985, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.20158624707371023, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.44776047557667586, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.557570822898273, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4125656013737127, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4889462808086373, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3471636178393148, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4191180487309204, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17493830569974406, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.26690261630673184, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1998573974138024, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.2618744307213444, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.13110052718009899, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.25678404806291744, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.35179752925748303, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.2246029757863831, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6417603075499863, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.37709297891717664, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6881502501430368, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5581982021478125, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6364887816884232, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5285087045343208, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.652013511062815, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.629039349740581, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.43795381992037963, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5881561248602009, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.46670957224939175, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.37544324742239676, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5293274846116299, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5344225462130586, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.49546288984677567, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.40577230815100285, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4519601247384226, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.41602211217571683, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.18842393723950338, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5622542444405211, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.42966520599840885, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.18842393723950338, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5646801080937621, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.41345800279862177, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.49713060327965375, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.16195570128532405, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.581645267684411, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4638613135486478, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.41734150775835166, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.429292711066547, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5848202846227532, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.41213231348812146, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40435987083533204, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.34256683873776383, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.41477028165511615, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40435987083533204, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.33319754264314433, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40854152133685306, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40435987083533204, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40435987083533204, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4164061298971701, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.34945014016328746, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.37581389131485465, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40562290854898025, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3327212134448652, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5709936728721758, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40562290854898025, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40562290854898025, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.46696436096182586, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.33546955366063214, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.40319099863003527, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39618802899930716, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39858613265631837, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3818534926571001, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3644112480028862, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3898236605340541, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3128264071150837, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39618802899930716, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3099872951741207, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3099872951741207, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.393379300802006, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3955832343987641, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.389666294007518, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.30325797018747325, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3066337968338866, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3892064098781075, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3010381621698183, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3118742681270173, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.393379300802006, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.28783297914763095, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3958941272081701, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5042211795038526, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.511876122662448, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.511876122662448, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5582360999449585, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4418365362317144, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5948724602646328, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5644198744535891, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4566163202450332, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5049375875723539, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.608796342723599, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.511876122662448, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5565173534238104, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5582360999449585, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4915933923809756, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4429196299668147, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4854320703575965, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.41469341972645324, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.39451521279220947, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5516607622642397, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.47160616105623426, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5256353512715748, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3765697091436241, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2534743707366162, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5971149415305869, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3431841258656284, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.27447938256311044, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.615291848344044, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2948993986902436, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5989264158576341, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2948993986902436, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5989264158576341, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.31573558123189943, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6989238098201116, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.12962472880491877, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5750206459290513, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.14296145628396553, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5102054230731641, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.33118227522229554, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7010244056936935, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6245952145297528, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6245952145297528, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2680165156355779, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5989264158576341, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2680165156355779, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5989264158576341, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.32594818888335836, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6263180162489238, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4425650919372919, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.32594818888335836, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6263180162489238, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4576529535952892, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5309982646782259, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4726395749383864, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.40052428191473877, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4214137028076755, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.2630268050449769, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.33762297226992255, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4279680255777309, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4179740300979212, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.39336600752225864, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.399524781060505, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3811737094308541, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5189004396088754, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.32094538365835024, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4101715667811344, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.45834841871997833, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4498692000973136, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4568577003687423, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.31754227193241025, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3974726419025883, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.24601372576927547, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6374693500772332, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1892240568795935, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6151179643430991, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.24601372576927547, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.686947433675709, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4746119151171374, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5833743057382133, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.195647514979229, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5832256253964303, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2658483576665877, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6410540990527072, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.23578316044531808, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6511343054546453, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.23578316044531808, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6511343054546453, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5639241776831634, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.46160726531733565, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.25336549464486463, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6437859092065046, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4513165758172509, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7514771576902608, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.23578316044531808, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6511343054546453, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5281061979991509, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5554602680850725, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.17181529671327242, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6053635787005981, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6520065459729374, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.41291750111233794, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.17181529671327242, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6053635787005981, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.46426595961938383, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.41238100267720657, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.41238100267720657, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4806367958084579, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.43269692060361126, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5066311799500233, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6562641136790542, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4494592020783298, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.45393803242035113, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5013632657267051, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.44006989470956354, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.45746339332244207, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.49118110181149666, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.49118110181149666, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4224991954993499, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5379068753129642, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5379068753129642, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.44493884815976026, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3348758882377771, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4601349893675622, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.410846945789476, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.39909989628767284, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.39913709020460375, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.40443357144012176, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.39909989628767284, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4354398635855642, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5705717737418762, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.40443357144012176, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.40443357144012176, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4121946181418776, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.40443357144012176, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4219530220129113, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.39909989628767284, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.41663636213344807, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.42422145417131013, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5606044053771457, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4276677753816098, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.40706217940224826, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.40443357144012176, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4121946181418776, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3113878808075066, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6758978744760765, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.17181529671327242, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5293474685884572, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.23578316044531808, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5821373704411671, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.14528679532351443, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.514952316880994, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.22894156860669912, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6314372536561444, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21972813874997157, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6022094443409847, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3113878808075066, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6728506998168392, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21305413619585087, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6284808905153216, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21305413619585087, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6284808905153216, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3128496839849598, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.1487964117124549, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.421318296293088, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.21899108456429012, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5773502691896258, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7999099314029202, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5323469509459265, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6371798394308665, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6423124418413864, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6423124418413864, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.470365760449425, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2970314818988727, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3292499962917628, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4410492519530161, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4429196299668147, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.47465074831919213, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4429196299668147, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4425973012069069, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.44024010151528153, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4550016613145898, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4440931655950853, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.44830378475308, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.47465074831919213, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.44830378475308, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.49360149005422826, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.44667985032715174, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2623399284064729, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4373156210032521, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3844263765000694, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3805770883173698, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.40508457369784023, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.39818525322365445, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.39818525322365445, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3844263765000694, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3844263765000694, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3830425592586042, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.39818525322365445, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6474126202050918, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5802683403568892, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5802683403568892, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5521590062829653, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.19923405658137924, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6211036406023237, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6474126202050918, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5802683403568892, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.18814785746917081, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.628558096175999, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.18814785746917081, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.628558096175999, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6131017059052001, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5513474668136094, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5513474668136094, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6474126202050918, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6474126202050918, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6131017059052001, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6131017059052001, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6131017059052001, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5802683403568892, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1423071532720465, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5673078468780355, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.19923405658137924, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6211036406023237, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3446073377034663, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7621696379946562, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3237722713145643, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7426638026175545, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.37030468338190614, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7587397825317436, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.545311114945696, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3392375549949802, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7348936586421482, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.14025775160081475, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5380752589178658, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.4637878319059324, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6919476196061328, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.17694975149532557, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5437152782473114, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1457684614972261, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5633850959085152, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6120635842558794, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.5303624596095554, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7835371347721495, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3969996397250977, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.7487402156832422, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.9260013112796359, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.37030468338190614, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7587397825317436, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5658596262915636, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1457684614972261, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5701800421590155, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.37030468338190614, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7587397825317436, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.18207052811092136, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5476571078959771, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.1711057433668069, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1531682455208201, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6009917293478183, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.25947507140745757, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6659437947666702, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.49342175914364256, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4754189767029448, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.46847165370535515, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.42156430044473914, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5098954559839274, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.13369377363079382, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5417128748379603, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5417128748379603, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2784899880299974, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6722683601585776, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4828085350127393, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3771310857613967, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6062665280777744, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.38053710786825434, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7011240864777649, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.293597382795084, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6760199025405591, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.27571859863660825, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.743408011301782, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6282512191941445, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.14253911354181859, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5429166339438998, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4088276333455685, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4745035227847713, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.195647514979229, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5725643788499303, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4352628824108997, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3620843366588185, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3550428472545064, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.18842393723950338, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5854975500881314, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3870105243407916, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.18842393723950338, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5854975500881314, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.49833704863382544, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.49833704863382544, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.327643461630417, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.29010990017245786, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.27366048131065474, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.20149416157064579, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5911912768187473, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.20149416157064579, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5931139543094289, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3782180895945298, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.507081939944787, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5076904123107298, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3643413837012786, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.16319679661526076, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3474927845768493, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5753050684342109, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5116862201536014, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.22131477988685871, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6188310784475567, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.49289897908980135, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5769327326081999, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6248961527161889, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.22179945921983923, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6249971903914197, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.44548434872692594, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.448224857029718, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.514391848002756, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4519657987381455, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5327944201340103, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.22179945921983923, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6249971903914197, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5141209056236068, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5121650809135759, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6248961527161889, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5216428635440964, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4564432184821405, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3555531255203411, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5116862201536014, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.520472515533923, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.33471616336068044, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3198143076622585, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.25944035160413503, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2975936119966016, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.33494612818381275, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.33494612818381275, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.23219780504948684, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.23219780504948684, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.38085857828188696, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.36702287443308856, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.37353268221130526, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5262688121999385, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.522087506283104, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.38637605442040596, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4054892447711709, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3835470698559142, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.33540675877467946, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.172700810315234, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.33494612818381275, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2961516536011624, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7355780986981637, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2865612242047131, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6433813179203622, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.26518122980477765, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6541173886447416, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.26220676436185975, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.646323175287155, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2722589423069702, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.658571547163188, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17694975149532557, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5836240065197391, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.28977907494497107, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6663117339552681, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.48426682761561596, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.48426682761561596, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5617057003908478, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.49912699124761417, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.25336549464486463, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6547636046715577, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6309937233948154, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6285229436299309, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6285229436299309, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4182671264424632, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.29254488484029956, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3040559696901293, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6658994383739726, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.43620605921972144, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3598792258309727, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3258323649865128, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3209186108619747, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5002716530045863, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5002716530045863, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4276859054768592, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5002716530045863, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5002716530045863, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.45100597619813854, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.44158982072668623, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.39176422032430464, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5211563282115517, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5459722940273104, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5459722940273104, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3258323649865128, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.22011791783839232, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6212521406814923, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5343147728119615, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5125809225356253, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5125809225356253, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.511876122662448, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.47825370157575003, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5059916132562515, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4813598669606701, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4813598669606701, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4813598669606701, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.47825370157575003, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.511876122662448, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4935153102946312, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.47825370157575003, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4935153102946312, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4935153102946312, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.47825370157575003, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.47825370157575003, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.511876122662448, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4646331830467803, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5063020142455625, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5539920925426138, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5539920925426138, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5633410521280906, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5963099883424426, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5963099883424426, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5963099883424426, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5963099883424426, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5963099883424426, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6265140753983048, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5138477284777235, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6265140753983048, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6245566175148537, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6265140753983048, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6265140753983048, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6265140753983048, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5539920925426138, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.27979820860022203, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6056889168578378, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5326397959358325, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5226572946586268, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5226572946586268, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5210387656594864, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5309753107573227, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4671158417621693, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2102369368326755, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5768887726639784, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.195647514979229, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5857714957546027, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.195647514979229, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5857714957546027, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.48085787079671877, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5309753107573227, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3859677866958932, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2102369368326755, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5768887726639784, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4824140720031325, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2102369368326755, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5876589559170592, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5309753107573227, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5309753107573227, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5309753107573227, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4814496481274858, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.195647514979229, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5857714957546027, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5073395824633415, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5073395824633415, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5054194884603328, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.49233042976388086, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4877445613866086, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4903188428039103, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4877445613866086, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.48911069552546027, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.47179783140068143, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6171472238624475, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4197983611654241, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3993213727535769, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5057748632231697, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5057748632231697, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5079994737492071, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4877445613866086, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.03502843507733942, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5057748632231697, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.31122692088261866, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5362380779055197, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.33709347944719925, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.29382595610734974, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.31966312198190094, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3095023687399762, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.33821252076454705, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.33709347944719925, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4148097947848928, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4216795433274884, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4216795433274884, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.39257815659454015, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4148097947848928, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.40151087965388177, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.33995727836928735, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4148097947848928, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4148097947848928, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4148097947848928, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4148097947848928, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.40848621046151223, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.31805405607794895, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3195891679001926, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3222538601891173, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7495871587703783, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5773664661124461, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1624355752882384, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6732778877516836, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3146660996956415, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.774919653861933, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7180407770761651, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7180407770761651, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7180407770761651, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.653546979730166, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.653546979730166, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.45984464012364756, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2722589423069702, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6049790801942001, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6277082350099422, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7180407770761651, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3222538601891173, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7495871587703783, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6277082350099422, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3222538601891173, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7495871587703783, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7180407770761651, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.18842393723950338, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.586796882410113, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3005283910333271, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2467789409989967, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.702397320872287, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.30577290788405437, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3053963874050995, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3025031428331747, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3038662664425978, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3463770747306081, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3323684721255328, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3437729074300146, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2984899750912363, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2984899750912363, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2982854478221892, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3038662664425978, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3758304027238242, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.342927504672789, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.33856457279955215, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3421048582632637, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3355517973989557, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3355517973989557, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3377353924432443, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3329758884511854, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3437729074300146, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4660343508894544, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43340932146378, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4169735477570989, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.43189251696918196, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.40242515214425184, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.46839189725195784, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.14962848372546667, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5531110803538978, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.48673932738045633, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.48673932738045633, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.41934944341336317, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3546654565919817, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.41134678748435993, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5026703894468475, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.44095987534978803, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5725197387086665, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4817075905641231, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.463520790843597, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4423536939689341, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2075521577117978, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.15980518115118317, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6117406545411793, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.21258844131063828, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6314891370223008, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15821285888349254, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6605676082065987, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5352059639541527, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4817621003925206, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6090533288062945, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6161305014329985, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20038908500140973, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6177327642561014, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4199711739851868, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4199711739851868, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.18710158230410626, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6827304460872186, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5106967338510985, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5084170678613665, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.21258844131063828, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6314891370223008, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.21258844131063828, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6314891370223008, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5220823443002603, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20038908500140973, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6177327642561014, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.17976451428761386, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6113954990048472, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.18710158230410626, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6827304460872186, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.44210435496259043, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3807134866446316, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6734021595321634, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5700887051433648, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5873831965245108, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.47099274965068205, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.41805694116981745, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5317734594035952, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4843771361283998, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5873831965245108, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4566163202450332, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4566163202450332, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3885961889310864, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.538750255869865, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.16097255887211387, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5719181187428595, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5719181187428595, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5599655154601001, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5719181187428595, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5148079777353672, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6408205679062159, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.16432863675964413, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.558984948114654, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.48231853956144055, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.37314692804855976, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4120675260154046, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4669656953948632, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4120675260154046, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4133673303529474, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4133673303529474, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4120675260154046, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4120675260154046, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43325089547434603, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4599966863788958, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4173344185979662, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4787742817228935, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43325089547434603, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43325089547434603, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43325089547434603, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.43325089547434603, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3756494330803333, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.40580143204058805, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4787742817228935, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1892240568795935, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5196343731603573, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4254686256509745, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3088290057043984, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.28985008910948157, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.20333448190047887, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.45391985808188723, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.22131477988685871, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5260789793410334, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.17694975149532557, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4902785344040517, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.18616493547741375, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.19343014224536145, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.19951581244033986, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.16605690899971173, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.15143107566514277, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.22131477988685871, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4362962278196088, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1661742929957894, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.46515980711224425, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4103552603347404, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1196655750514248, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.43807296710349614, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.449673018038321, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.21326736707612118, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1790439216234942, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.30577290788405437, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4271693186358773, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.44583799328544693, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.44562997179553193, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.394895635806623, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.456896886562563, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.31967472422535054, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.20793313992045814, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.33030039979994785, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.33030039979994785, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.24831335764102336, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.31718447830263197, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.17332651755199632, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4334317870334209, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4317729593125941, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4711738743510459, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.41527307940938124, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3909799362645297, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3032776840667523, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.012870012870012871, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3452137418984674, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.2887138086538547, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6342291345998248, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7013062757071812, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9303769449292738, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.2381658499765768, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9063898435384111, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5360330312711556, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7676864590616368, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5309354663044072, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6756014232714684, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4529852871970908, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6941474239078328, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.9457416090031758, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9892952933418456, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7912619863720214, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9129058871674676, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.9457416090031758, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9892952933418456, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.5087473540251254, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7647955332172516, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.5087473540251254, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7647955332172516, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.5087473540251254, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7647955332172516, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.5738396574789242, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.798357133373606, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.4234885228074744, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7410180114887145, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47375069012411286, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7543919667018285, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47375069012411286, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7543919667018285, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.5738396574789242, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.798357133373606, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.4234885228074744, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7410180114887145, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.47375069012411286, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7543919667018285, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7829685247145245, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7829685247145245, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6626129614342791, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8597893117683423, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4441961115027302, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7565542718609186, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.2828367156737383, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.37810687864454173, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.741392727905101, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.37916211129533023, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7363359547185945, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.44543578807748957, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7513336773729535, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4814564802258215, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7621649608882223, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3088448141335011, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6673372115834423, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7829685247145245, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5461499540157965, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7954823723658209, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.44543578807748957, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7513336773729535, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3363225191015943, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6803949682739066, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2404315522172745, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.49155714102395526, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3477250470582593, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7188419868243952, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.404727200247809, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6681898017773897, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.40276720463657734, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6529271690805427, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.404727200247809, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6681898017773897, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.404727200247809, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6681898017773897, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.404727200247809, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6392900613840917, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.404727200247809, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6681898017773897, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1990581597344524, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5898277017367236, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.404727200247809, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6681898017773897, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1990581597344524, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6133817758391366, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4386229919587297, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.44897710722021167, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6862249089515978, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5379348324975908, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7703766110349561, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.30188353873287377, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6086565367747951, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.22391522968021457, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6087618281135659, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3025029865727436, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6057244918018514, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2795351131184338, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5735871310845391, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.20776569671187678, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5495289426480258, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4621757041594117, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.22067731046885494, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5635661737033422, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7829685247145245, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.6026286934891149, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8025775976044891, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.6626129614342791, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8597893117683423, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.6626129614342791, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8597893117683423, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4727805712999679, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7717158158167359, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4063022828070774, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7128058030788165, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4063022828070774, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7128058030788165, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7689532399280165, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4441961115027302, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7565542718609186, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18117610753900412, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5900497114648452, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5461499540157965, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7954823723658209, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.44543578807748957, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7513336773729535, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.37192780061868996, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.647030498607364, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.24011079455637607, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.19920494035049138, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.614209720001149, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.5896613549548209, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7528914749586836, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.5300714512917181, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7461630750708693, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.43007078231141604, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6680243275130087, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.33359103227594633, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.701102363286568, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2565271158193808, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5754598856447696, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6423472232689572, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.5896613549548209, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7528914749586836, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.5271017464925504, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7749613594649343, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4596980088392874, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.713787745993602, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3014335251508215, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6287268013420879, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4335364472118335, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6878319610579101, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.480771131185851, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7032048786770096, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4801289744823913, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6766690087429765, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3272712268138726, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6272846474183881, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3272712268138726, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6272846474183881, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.30421485886156485, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.566236392445952, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.32078739729528816, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5817366082116868, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.32965129549221617, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.623436907204599, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.24706467963183681, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.18623343474790552, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5383789355001968, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.18623343474790552, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5383789355001968, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.32965129549221617, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.623436907204599, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.32078739729528816, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5817366082116868, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.476501312022118, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.32078739729528816, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5817366082116868, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4919440349584284, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.32078739729528816, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5817366082116868, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3231203125477008, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5812275690118908, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3231203125477008, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5812275690118908, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.48726470075632883, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.44332438338421004, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3231203125477008, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5812275690118908, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.28489318277723963, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5764325110247531, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2981792160679168, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5788026000794341, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3942058093215873, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5878575558111695, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2981792160679168, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5788026000794341, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3485799122645514, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6090575371936678, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3665134361137304, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6118771029352303, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3665134361137304, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6118771029352303, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3556254905627724, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.611063921488713, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3556254905627724, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.611063921488713, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3485799122645514, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6090575371936678, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.35870004213153, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5554477617576271, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.25590356077469273, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.527590401388296, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4085639059221913, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5887623870312143, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3485799122645514, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6090575371936678, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3485799122645514, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6090575371936678, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4100134571476398, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5856608401367807, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.37392149096896676, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5833802647068038, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.24987807848117904, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5493430788000264, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.17098323692758396, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5216877937894046, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3527295712700594, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6062826429226292, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.6471892368478446, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8142499721936278, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.7012294787544179, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8478115719875968, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.40202477345336673, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7469480084357536, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7829685247145245, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.42612283570374254, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7185121839177114, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.2799331151961311, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.20781449703060773, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.25958657290343434, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5698163692393635, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.40157733283424196, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7133166401137868, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4625957988586645, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7341375356694393, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2915369229944523, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.562240894166207, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.290046956468694, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4625957988586645, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7494665344743727, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5490659903839784, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.17729842264695017, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5199388279318895, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.23141570376732995, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5938624587877649, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.23713320246552005, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6106842970161642, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.21690365808279138, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5384773678665918, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.23114663823833642, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5786592584609213, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22128776529156546, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5609439249510223, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22128776529156546, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.572263303016663, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.21690365808279138, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5502221839528678, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.23114663823833642, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5786592584609213, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2371332024655201, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.555256623366109, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2371332024655201, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.555256623366109, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.1998573974138024, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.540043957078071, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22656720908801994, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.553314787782705, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.233078149078302, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5966212933325205, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3282518529729176, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6453010665294326, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.2124551208803614, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.30752616970214336, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6051452460471443, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.310441435588881, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6413164971104282, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.310441435588881, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6368374223560669, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2080315522738391, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5483451429916664, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.23114663823833642, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5814841210741494, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22656720908801994, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5465750236858569, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6888365053466561, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.8656273480576243, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.25711386542134795, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6088853751738869, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.25711386542134795, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6088853751738869, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3416581331218724, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6578570934289981, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3060368950930089, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6736142284622013, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.629934465484704, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3060368950930089, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6736142284622013, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.629934465484704, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.629934465484704, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3423591961656694, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6570214418399444, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.47986315176610383, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.335386511803452, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6803949682739066, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6888365053466561, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.8656273480576243, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6195872175593368, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.629934465484704, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3060368950930089, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6736142284622013, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3423591961656694, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6570214418399444, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.2281399713503153, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6211104268881504, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.46965980060137014, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.629934465484704, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5069487414732323, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7801245319017357, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.6358974376699329, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.736661937085844, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.45307778036928104, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6935397252637394, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.45307778036928104, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6935397252637394, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4719458927872361, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6691100411531956, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.43385612637937937, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6652156431356278, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4085639059221913, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6786065713232268, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.30614023358320086, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5870676308171808, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.2281399713503153, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6211104268881504, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7196315267102845, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8835331636515565, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7667541011433795, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7667541011433795, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7196315267102845, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8835331636515565, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1815358071299676, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5527491412738096, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7196315267102845, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8835331636515565, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6289868866690355, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7818060345351223, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7196315267102845, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8835331636515565, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7196315267102845, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8835331636515565, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7361065921505279, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6026286934891149, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8385943306861641, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.480771131185851, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.705252762035012, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.445107576642247, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6955301378913092, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.40157733283424196, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6532350818978572, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.38091370416670794, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6438225861756911, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.31374450602681464, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6422405832556486, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4924584878270648, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7062510642584722, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3132768114661938, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6093422256500997, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1624355752882384, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5090396683756193, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.30752616970214336, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5976254557718147, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15083364266523736, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5008630255601011, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15083364266523736, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5008630255601011, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.36227557436010244, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6470050797908481, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4246163317880344, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6588756520218197, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2927057121559396, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5325023221897424, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.45506803308128024, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7117510256855165, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.44903323241491255, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7473828748083323, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.419468515826214, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6664000694648706, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4938015541936678, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7820348786317745, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.32263864160302524, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6368573348787729, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1712473044894657, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5194487191479099, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12858902882463452, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.35477908164501704, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3942058093215873, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6316031412228033, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7202697992734389, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7202697992734389, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1943759862788499, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.49688103957939267, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1771210219016553, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4606490636515431, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1771210219016553, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4606490636515431, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.5461499540157965, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.798357133373606, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4676203687925029, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.22848056414159593, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5972946651297018, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7046532915279582, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.26660603480752404, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6007386267555782, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.11970700565377682, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.23357697166633196, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5582260842665357, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3903594390682207, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6662116837137958, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4727805712999679, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7717158158167359, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.36816017035411847, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6630063658071765, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.37456535742007424, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6126780725749296, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.39520818104058075, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.24363783193706642, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.36314748337164254, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7016516453748962, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.36314748337164254, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7016516453748962, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4335364472118335, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6966914157873363, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.6096687386093484, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.737928890860239, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.15774545980684188, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.510914938532951, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.39174440233850644, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6762795187534849, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.24363783193706642, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4526810222444627, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7303764654257315, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4393160369685383, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7326708250282779, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.43769127523507534, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7001859044467704, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.29742953512013587, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6260896463225846, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.16449149670902838, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5337097549575721, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4719458927872361, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6863265729154345, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.5309354663044072, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6990707992725005, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.43385612637937937, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6552557413442657, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4719458927872361, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6863265729154345, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.637202263020122, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7346216972763816, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2925712720836999, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5502827901617849, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.6349495142258627, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7749613594649343, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.6349495142258627, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7749613594649343, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.6349495142258627, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7749613594649343, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.37973023491174585, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3902414128366543, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.26963095785890817, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.5695988432761473, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7516103467926585, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4598036015897535, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6256401299595566, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.43385612637937937, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6552557413442657, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4811256400535275, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6745199184860661, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2503023845012661, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5179835315406534, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.32084466348045076, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.22063120635885589, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5852924591274146, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31008822704072875, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31008822704072875, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31008822704072875, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31008822704072875, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31008822704072875, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31178219518131567, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31178219518131567, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3836374068673084, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2936418375689259, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.26710323996759094, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1673872929477023, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4506667273103674, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3114749711831053, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31802371065401513, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.31008822704072875, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.22894939325531252, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5747669845604989, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.27545321289806546, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6280000881172884, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.22894939325531252, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5883432091316184, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.166352496246992, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5330423528994436, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.224188058954654, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5978847447208526, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3500905496410207, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1378592993183041, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3954726082641455, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2680165156355779, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.545567244447617, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.25376192011637994, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6052149632449516, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3631421561362529, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.18824072812426187, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3086172473271798, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6217822674304354, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3086172473271798, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6217822674304354, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3086172473271798, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6217822674304354, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3423591961656694, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6803639512204375, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.36539169772085134, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3411488281065382, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6740035136770584, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.7221847203387323, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.8931067231936596, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3416581331218724, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6578570934289981, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.92923260511913, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.23357697166633196, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6610479563844994, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.21270024173913482, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6183813548597394, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2281399713503153, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5664428061469187, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.19920494035049138, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.614209720001149, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.23357697166633196, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6610479563844994, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.23357697166633196, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6610479563844994, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.23374920560961487, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6381858968225665, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.19468124777669177, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5932036830661304, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.1990581597344524, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5425407305974037, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.5401725898595141, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7497446479932584, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6211104268881504, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.220294066346937, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6375628454216249, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.6026286934891149, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.8385943306861641, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.6026286934891149, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.8385943306861641, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.22012248449054683, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.647344487348367, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.13737279171076758, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.42785667387454995, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17923344640485428, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5211683330085515, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7342525133793019, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4797543511401896, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7240781310560407, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7342525133793019, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7342525133793019, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5420890779002704, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7219273458493682, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28943182557959846, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5795851744687439, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7644556249154987, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28943182557959846, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5795851744687439, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28943182557959846, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5795851744687439, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2677353447271197, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.569529411820844, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5420890779002704, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7219273458493682, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.15821285888349262, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4886015917518962, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5072784644062104, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7342525133793019, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.17793925745339384, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5497069221194746, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5679161104357995, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7564733289707379, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5679161104357995, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7564733289707379, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1712473044894657, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5194487191479099, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2567770437062668, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.38457089506267517, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6582292681072595, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.6401876410870359, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.7526484951226097, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.5184341074271375, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.7295047041623038, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4252502464011162, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6774296788457803, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4252502464011162, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6774296788457803, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.18543829210530705, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.52927058814847, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.14107526427034148, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.18623343474790552, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5348516130206653, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.18623343474790552, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5348516130206653, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.42643704825557327, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6730449758221991, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4252502464011162, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6774296788457803, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.185715135067742, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5098093454005965, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.42643704825557327, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6730449758221991, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.12497004250886251, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4252502464011162, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6803639512204375, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.28648682864686603, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.543546241720005, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4252502464011162, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6774296788457803, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.18543829210530705, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5283005433854684, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.20313747122261766, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5392632080295834, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.18623343474790552, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5348516130206653, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33057129676705455, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5669225664686625, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33057129676705455, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5669225664686625, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33057129676705455, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5669225664686625, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3240220869485148, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5364140651922888, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4301823405286034, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4301823405286034, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.24914989711092594, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4320304661292458, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4320304661292458, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4301823405286034, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3240220869485148, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5364140651922888, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.41768335112041305, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.41786513699087335, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4301823405286034, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4084622939366714, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33032772118856274, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5637799127470854, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33032772118856274, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5637799127470854, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4301823405286034, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33057129676705455, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5669225664686625, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4301823405286034, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.5468017145144113, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7519227909172003, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4790714250659131, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6938678729026243, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.480771131185851, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7084427046662088, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.480771131185851, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7084427046662088, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.5420890779002704, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7268331815757023, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.5420890779002704, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7268331815757023, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4186091892833126, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6654623051601114, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.6004981752197522, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7697646564917222, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4186091892833126, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6654623051601114, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4790714250659131, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7010793195917541, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.5420890779002704, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7268331815757023, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.617939643800199, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8356543644789964, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.617939643800199, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8356543644789964, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.6526460174517784, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8267638445308375, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.6912804407652906, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8416888527493164, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.6912804407652906, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8416888527493164, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3025029865727436, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6057244918018514, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9027320255916917, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2704091953828695, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6207272323003366, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3386854985606571, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.604413581883028, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.7663313999772253, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.27720938018510377, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.428047180290638, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30350690419450826, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2813985981593422, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.28107488868712643, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2954873212263811, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2974410142531065, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30042054271881197, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30142704700265815, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30142704700265815, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3334615788010355, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3018990564467044, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2688025405888032, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.29942074717273737, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2982195617869878, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.3050638713235347, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5082087402765254, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30142704700265815, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.30142704700265815, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3444107902907301, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2773273497281852, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.29942074717273737, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.6281881652405527, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7361567090943679, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.569133886912883, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6834516951654327, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.16807611261595506, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4597054186181326, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3343063479794574, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5429171669983389, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4504780990115136, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6386322492678208, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.21555378801920327, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.48837390458060403, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.22847893469128855, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1512514932863718, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3515865992727904, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1512514932863718, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3515865992727904, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2915369229944523, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.535395621261131, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.40910310335214356, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6380312874183272, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.5650247638590733, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7341016750688163, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4504780990115136, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6386322492678208, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1813423031516851, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4592771215097494, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4504780990115136, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6386322492678208, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.623652672746999, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7064310568035931, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.40910310335214356, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6380312874183272, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.33132739382030574, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.21241088191397664, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.21511238963872098, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.48967538401421223, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.27249745234058675, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.576487806400357, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.32078739729528816, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5779838399768712, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.32965129549221617, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5788023273137882, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1860962119549805, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5438504570088443, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.17923344640485428, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5428745815211856, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.18543829210530705, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5354482399943388, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.18951629567590744, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5515559648122452, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1860962119549805, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5438504570088443, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1860962119549805, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5438504570088443, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.19032892442937785, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5194565258434112, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.18437427949667837, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5211412954589442, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.18107197870881736, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.533623377476928, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.548958765126221, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7425459638873632, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3365047447281543, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5791325287918098, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.18437427949667837, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5211412954589442, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3365047447281543, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5791325287918098, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3365047447281543, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5791325287918098, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.15071676257541072, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5080729257689284, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.14598608091257087, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4458625802506543, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1860962119549805, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5438504570088443, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4814564802258215, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7954823723658209, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3742893656007335, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7582803042224814, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.6316839256114659, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.8143078359179658, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.5069487414732323, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.8112065454752675, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.22012248449054683, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6156007392092506, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.25811803218589047, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.31186879016424773, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6488151565290091, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.31186879016424773, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6488151565290091, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.44543578807748957, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7492834759166062, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.19920494035049138, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.614209720001149, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3025029865727436, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6286065041873574, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.20031295840594252, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.17509131039045966, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4886834175779622, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.15573964185427053, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3372949202573946, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.22894939325531252, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6048598347770396, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.602867050301643, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.8176176657543648, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5386695403411698, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.378882732439682, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6841096204411963, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.631218480549812, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7874289440091755, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.19865054013223624, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6164064592365338, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.12858902882463452, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.44304178293591645, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3283378949269553, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1897992267368494, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5849112100276023, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.5718109192406814, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.798422026035913, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.631218480549812, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.8445422169928634, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2111187176080899, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6020583416224236, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6947687298202525, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6947687298202525, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.46992509483298506, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2534837513667069, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7538467008030766, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.47410002229034043, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.671938683171001, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5206571060403834, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.689324258927, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.30344371233327844, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6219235056961488, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.21555378801920327, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5577976700241679, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.44119978444380453, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6860816819201474, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.18728674627858763, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5182121492744396, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.17601203382268035, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.16253030682894548, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.31575942061963186, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.16253030682894548, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.31575942061963186, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.21030548059060677, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.14495639555867468, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2909086706553049, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.0921413422353044, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5091224918749461, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.7202697992734389, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.258900870705422, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.4063022828070774, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6789996206024372, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3957399456352439, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6505957913794083, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.36039626112317097, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5998911326651838, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.41443024325505773, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6439781798190682, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.11217219041746629, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.27571859863660825, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5218771218644234, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4174441728660793, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6692136096184196, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.39811631946890474, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6320908834639722, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4174441728660793, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6692136096184196, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4441961115027302, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.7565542718609186, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4174441728660793, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6692136096184196, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.18003301924565476, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5051819537131238, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4174441728660793, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6706681340881337, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.39811631946890474, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6320908834639722, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4186091892833126, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6649304720642071, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.17837875461384597, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3984098807009828, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.636016958488394, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.17150296156301634, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.48812954881732445, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.46076979395163187, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.39000168645396877, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.35094536062899695, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.31569611706824424, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5247546298443336, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.45573768632726, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4794224895461657, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2744128100994792, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2744128100994792, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.29898487912917937, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2556170391311767, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.32927415290866546, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.402200098075857, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6018817450865662, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2978808647663532, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5140749054213731, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.22848056414159593, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5921402782211889, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.21511238963872098, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5217348733264977, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.30376137001310205, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5156956617625708, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3377499269000448, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1513630224364002, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.32937492594263224, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.18879521773374403, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4618333673677675, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.41682189465797687, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6573099561830166, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2852636439147137, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5851048071392815, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17636478563502966, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5283932773245016, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4203546552244347, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.48181149445310956, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.7675828789334244, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.34831550233828484, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6924946723825833, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.29623686353922923, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.22907781804002908, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.22907781804002908, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1196655750514248, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.29141398801197316, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.14025775160081475, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3031509137265966, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.14085916416769417, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.25076903008051404, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4814564802258215, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.7621649608882223, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.6917901740466924, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.8479928839177578, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3088448141335011, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.7035462512447451, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4186091892833126, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6393114196475629, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.5465526716276092, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.8012679276648627, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.18097539697008458, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.11856660123276004, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3311682798096144, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3164257177669852, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5851860325042342, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3263040636562357, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3390387389794623, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6170420596680538, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3142665434344143, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6466526067220029, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3751840463233443, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6279894552667558, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19268479640608693, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.551397074868541, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5838790966762375, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5838790966762375, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5838790966762375, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.4797543511401896, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7571314915469349, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.4797543511401896, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.7571314915469349, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17470942957770763, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5403400891349619, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19268479640608693, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5436964586887773, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5763410052067085, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.3060368950930089, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6498981440676681, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5838790966762375, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5763410052067085, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5838790966762375, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5838790966762375, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17470942957770763, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.581881475681913, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.24343304284910333, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6275577931282961, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.28571962561926445, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.6431872581462166, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5014756677893482, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7958858211784339, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6255340042200862, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8724783049357475, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5014756677893482, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7958858211784339, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3083012995502152, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6589376390020449, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43021236941942204, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7142896582178452, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43021236941942204, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7142896582178452, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4216890913810254, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6885217194158456, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4216890913810254, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6885217194158456, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.4216890913810254, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6885217194158456, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3083012995502152, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6589376390020449, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3390387389794623, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6743433920357993, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30166728533047465, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6331697020750404, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6255340042200862, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8724783049357475, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5351607207631776, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7900844096102096, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.29176300840900793, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6143650111703199, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5014756677893482, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7958858211784339, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.5014756677893482, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7958858211784339, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3825188992413085, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.7407084022031544, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.24090844358935917, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5468852870478801, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.6255340042200862, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.8724783049357475, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4481489512240194, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7745649676018984, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4896430866960958, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7638521785649908, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.7411155087367244, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6509517796070665, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.38513414673376833, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7005713730032203, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.39545121937832856, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6963801389253689, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4101479464529936, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7041976254287654, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4547900039222725, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6541971428810075, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2919394073770869, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5957961314949175, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.17537670874647399, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4800889669735933, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3382865300192028, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6408187443698572, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3347189874003768, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6644203374869264, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6991726442472661, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1684221470406417, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5314740727463538, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.38416065466563115, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7278436878265722, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.22845493240080628, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.584996891148118, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.38416065466563115, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.7278436878265722, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18830095106396066, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.519072776559512, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6991726442472661, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6991726442472661, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.38785611216800814, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6673259967761724, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.4547900039222725, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6556658100891058, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3675667565747676, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5884916014203391, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.16331948281960493, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.350650198151987, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.8056920633274978, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.8391519966182309, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.595092211343687, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7971172820981081, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7122562458056777, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7122562458056777, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4207937380724192, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6985308026285912, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.651158213392685, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.860002370506267, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.8020845125558708, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2308087288583725, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5837900289346171, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5110827761016288, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.27571859863660825, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5884245635756674, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.595092211343687, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7945212279546889, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7122562458056777, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3675667565747676, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5700185304500285, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.43011383006801057, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7140577175386648, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.18728674627858763, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5160823886915287, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3843363395779093, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.32263864160302524, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6824395076981005, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4896430866960958, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7719180936906627, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6590438071804039, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.32263864160302524, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6824395076981005, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4896430866960958, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7719180936906627, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4481489512240194, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7745649676018984, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.38305978177479755, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6061131723054572, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.34636800712900173, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5167955767158704, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.3675667565747676, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.5397693417183738, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4803501444747088, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7417101158248365, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.421151249507493, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6889522290200047, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.38687573986922297, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6607831957682522, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.38687573986922297, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6607831957682522, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.425143650778693, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6674242019044293, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4803501444747088, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7417101158248365, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4803501444747088, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7417101158248365, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.421151249507493, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6938674571170766, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.41368954504257266, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6745746194667386, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.421151249507493, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6889522290200047, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.41843795218458035, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.6316283876832989, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4803501444747088, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.7417101158248365, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.42221847853238736, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.6656008733100179, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.38513414673376833, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.7005713730032203, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24047860794644352, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.58198979036704, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4481489512240194, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7994721822064033, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.38754077501151757, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.598503332887995, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5124776602965491, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7722874800637285, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3942058093215873, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6619197609807324, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5124776602965491, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7722874800637285, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5037141288692649, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7451862558478656, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5037141288692649, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7451862558478656, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3291598889023262, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6085546680624175, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.23551878211683616, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3575980447629419, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6173766800527999, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.857390040146912, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6173766800527999, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.857390040146912, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6173766800527999, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.857390040146912, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6173766800527999, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.857390040146912, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.6173766800527999, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.857390040146912, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4481489512240194, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7994721822064033, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3470839302425112, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4845766087853281, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.7138566289355139, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5512324461754572, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7289444696770301, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3737098172408067, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6832201170000932, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4481489512240194, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.8268199262002004, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.39159269732992946, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.7803080344509848, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.22436571657855092, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.61166969974579, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5512324461754572, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.22436571657855092, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.61166969974579, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.22423870508323301, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6366515193698862, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5582775802710993, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6507561416639396, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8215788698315908, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.6507561416639396, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8215788698315908, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5967384019266717, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8544348080833218, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4896430866960958, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7638521785649908, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.7317734491561229, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.251696695878184, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6180491939580447, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5967384019266717, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.8544348080833218, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2719326877457978, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6002086362682414, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7246227738353674, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7211812032548905, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7211812032548905, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7246227738353674, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.28592291256793106, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6102727682426059, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2748202507307579, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5810363959809548, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.28571962561926445, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.693456244639743, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7395804946242599, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3684981984538114, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5606332518476288, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3694816688798906, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1423071532720465, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5234276250101042, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6532234058412462, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5432206404657683, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7121135616759211, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.17855149299161602, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4966305184761827, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.23418123261847468, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5587864404094985, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.8020845125558708, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.43373675317548144, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7025336737339543, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.36802977705844575, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7369844404912368, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7395804946242599, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.20826058354833846, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5799650985757929, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7395804946242599, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.43664808203158506, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.294467310498826, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4554141323944355, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.7121135616759211, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3201911827891037, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7182383858693244, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4536404448264584, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.8020827133708689, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5134477225657772, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.22831386795944372, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6930977635889574, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.22012248449054683, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6169942315547352, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.18818468056723414, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5492529967313384, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.18818468056723414, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5492529967313384, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.20617350508583818, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5529730302091665, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.21644311639014951, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5920345924272161, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.25755472674357427, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7079787462750899, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.25755472674357427, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7217376192850543, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.25755472674357427, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7217376192850543, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.22012248449054683, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.6174396094425288, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3142765374520343, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3060368950930089, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.7004749900624669, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.8084123599808738, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4545091839935173, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.7166050399790445, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2919394073770869, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6265777781732258, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4345673759957651, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.703388118507387, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.44036190349192267, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.44036190349192267, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.43485418354574973, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.24609170069111483, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.22752748300913606, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.46867110147752883, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2917591430729611, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.64776154598388, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.17793925745339384, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5258943316166202, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.24939081998882368, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.35818640176176625, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.723627810424739, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.4812700337596407, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.7668482135865776, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3370129264673147, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.7096874943799061, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31771674795486515, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6550628376568252, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.19910401453355991, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5815343547138478, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1624355752882384, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4952968469712617, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.45307778036928104, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6384504056254413, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4201902477742268, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.23185078121230157, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5831825813678972, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.40176661207669695, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.12648351910430983, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3806304275656041, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3806304275656041, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4741401979744739, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4288827686761902, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4655976516174543, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5687448979662939, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2908402945446888, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5817930307429677, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3800213082631731, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5676463425230758, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.27587476896182844, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5801799655962208, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2111187176080899, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.535975670216605, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.21001906325619232, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5151695082194717, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2543881726648529, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3099293756712212, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.37489047453628294, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7155230965848066, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7807505267551733, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2697856975860103, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5736298373015629, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3766019021279213, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7318674193893624, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7807505267551733, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2604066818943325, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6461214650335204, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3766019021279213, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7318674193893624, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.36800882629132287, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7348407723095736, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.36800882629132287, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7348407723095736, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.20390514683548702, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6747066998707847, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.8131513745396886, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3407563025626974, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7443887915363598, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.6700420356552951, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.8131513745396886, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4909136024426773, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.8295116386418164, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3766019021279213, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7318674193893624, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.7807505267551733, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.19268479640608693, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5168612893142901, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5084550790849273, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.1832567180568652, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5727346150299959, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7246227738353674, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.5595205105615875, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.8322210048001876, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7246227738353674, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7199991365237522, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2821801681960571, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6827049750669753, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7246227738353674, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.28592291256793106, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6102727682426059, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3171094709345114, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7045234516083255, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3942058093215873, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6697898834930974, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3142665434344143, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6466526067220029, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6934309279690296, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2453392175275486, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6569130291153491, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5760406199498378, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2046592065585361, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5835189337715896, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3060368950930089, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6834837188844622, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4797543511401896, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.7550938397535033, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.20313747122261766, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5506087730896332, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.20313747122261766, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5506087730896332, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2046592065585361, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5835189337715896, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4896430866960958, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.7815961723922495, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2046592065585361, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5835189337715896, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3763693611344683, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6360504215730572, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5760406199498378, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5760406199498378, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.29170205300854224, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6498499527552988, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.14728212724124629, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.485741585706456, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3733543476417276, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.538395940979961, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1973212456326944, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4151043049244464, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1973212456326944, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4151043049244464, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1973212456326944, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4151043049244464, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3733543476417276, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.538395940979961, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3733543476417276, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.538395940979961, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.20763578034718042, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.46035934390642647, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3733543476417276, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.538395940979961, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1973212456326944, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4151043049244464, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3610544299180199, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49125115898082056, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1973212456326944, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4151043049244464, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1973212456326944, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4151043049244464, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33891487511850005, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5365882254723207, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3733543476417276, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.538395940979961, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4284945090100314, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.7164026439677106, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.33464494273746426, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.6344206060206898, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5848344753614038, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23198210427894825, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.630711601223299, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8578928092681435, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9422733087334002, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8578928092681435, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9422733087334002, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.6734648419604768, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.7694606959147566, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5397323593778651, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.7889494278008897, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4803501444747088, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6901644027400852, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.8578928092681435, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.9422733087334002, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4929664394953523, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6587225864765196, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.442444266172892, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.6752890127907986, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.23487811400114963, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.35937816565888026, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.797323390576564, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.4896430866960958, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6750223515189266, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.42818224355402373, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.667901678840575, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2453392175275486, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5365332655663203, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2910624919304027, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.525586298564604, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.32263864160302524, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5322085776775811, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30041915229862387, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5110381669871915, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.28571962561926445, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5009118094880767, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.28571962561926445, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5009118094880767, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.48707827505552054, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30041915229862387, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5110381669871915, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5111162100323225, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.28571962561926445, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5009118094880767, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30041915229862387, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5110381669871915, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30041915229862387, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5110381669871915, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.30041915229862387, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5110381669871915, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.28571962561926445, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5009118094880767, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4848369352570916, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3677323079275383, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.22738612304909625, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.47454858661827737, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.38687573986922297, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6514359547109982, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.42105372680687736, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7001171094008295, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.19910401453355991, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5338904589112099, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.24233572351352062, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5675102323575353, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.44327096902711544, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4245201692926341, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.4803501444747088, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7417101158248365, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4614951111675217, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4614951111675217, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4848137281002213, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.38785611216800814, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6213964982068823, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.22608614921612638, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5233340279272971, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3416198047295219, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6421557564106395, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.38785611216800814, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6213964982068823, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.38785611216800814, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6213964982068823, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.38785611216800814, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.6213964982068823, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.47134770123856895, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.33425592140853283, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.38513414673376833, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.7005713730032203, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.4881010344921759, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.8110307349404526, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2767906930665974, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6946453530067933, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3685289119518547, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6989312471477999, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.32393211943598493, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6439540125824591, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.32393211943598493, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6439540125824591, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.5183282721440023, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.824367835388174, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3865584077322271, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.7076640192892537, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2644894679721535, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6377622807212552, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.19547215688069816, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5978847581113598, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.5183282721440023, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.824367835388174, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.42984824697674956, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7395804946242599, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.527528099078667, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4094709585736592, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.47384807927636907, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6506028604680089, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.21576146358278564, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5945881910966203, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.32365795029773287, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.7121135616759211, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.375322162926944, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.375322162926944, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.19268479640608693, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5479565964904024, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6506028604680089, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3683270402125527, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6506028604680089, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6506028604680089, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6532234058412462, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.6532234058412462, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.19268479640608693, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5505445890664655, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3765285487977598, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3567823943323416, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.21576146358278564, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5945881910966203, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7076271819674439, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7128603669502883, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3584668928097086, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.634863098567942, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3584668928097086, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.634863098567942, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6266330371317139, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.24456656109396324, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6506028604680089, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6266330371317139, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2998634479378894, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4724747576866367, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.31142220978542806, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5393731664820625, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7128603669502883, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7128603669502883, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7128603669502883, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7128603669502883, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7128603669502883, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7076271819674439, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7076271819674439, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.42195777059677314, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.7076271819674439, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3589120626864888, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5425514102500383, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.19415472735264994, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.41508997974031253, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.23972125922151485, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6266330371317139, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.42062888241722096, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6813469636986809, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2600960555023324, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.19898107345153532, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5339708887761974, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4770332228554784, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.21644311639014951, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6255338654372382, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4394721549501124, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20390514683548702, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6152907875442002, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.40305334040893576, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.40305334040893576, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3490251488234659, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.14832342806480867, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.33219031071031885, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.16712370229561266, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.48994561421713123, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.8020827133708689, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.39545121937832856, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6822216627082669, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20313747122261766, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5634928669626099, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.34822073619539046, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5822525754254643, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.41763594575087865, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.17389434573554247, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.24233572351352062, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5561045459288251, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3942058093215873, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6294033705157869, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3942058093215873, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6452705345581219, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1712473044894657, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5272789142558241, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2111187176080899, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5086920944994741, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2165768464503216, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5453742939698616, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.44787223195695314, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.7968980206907678, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.15929050399664219, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5414849269145706, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.31671615012203974, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6782734900436637, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.39545121937832856, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6541357656856408, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.43281826407421803, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4282924873829561, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4056299814865685, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.18413533063377066, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5210859722276246, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2573956940045279, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6452211051786294, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.4909101855057947, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2620612021069097, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5135749478743646, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2620612021069097, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5135749478743646, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.20028107620075963, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3719830026822787, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3137810587035114, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.39569555015790975, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.7071407148576546, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.334851704167788, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6039857021253505, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.28615556452106294, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6299182889624744, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.33464494273746426, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5983196805551743, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.33464494273746426, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5983196805551743, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.285110649893058, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.18961526642588783, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.334851704167788, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.6474532635641537, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4787974949414673, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.713332477096005, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.32952451615212436, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4924875778629721, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4021713045548922, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4199894418900964, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.7020733406320506, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2256540129692241, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4590213069261372, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1974694070034893, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1754193437062364, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1785676020318168, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1842384650009126, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.18458233680118352, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1774601133769828, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.5383680940297331, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.786096406361039, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4787974949414673, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.713332477096005, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.20313747122261766, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4583712036944982, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.39936742298908956, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3981749822565199, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2404315522172745, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4283144598181996, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1641956652179752, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5508394512324739, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.17905278399134197, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.37257295447029826, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15521606028436608, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.37645329404497957, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.12620429887108936, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.35580703793872603, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.12872220631084524, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.33602633953270183, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.14465783975603244, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.30302832149927306, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.10316589800033629, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3117209570799365, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1582866049832572, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.34487142413575794, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.1914846465507395, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.21374300348268538, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.03037224815656603, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0692157910411486, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.2170093014574072, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.042575418285137674, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.05173688961049459, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.306354798881405, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5275640293284548, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.2734283774929853, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5252214120598302, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.10203846572325131, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.33381153680096753, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1685643537060726, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.36926449644166065, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.28110751553747226, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.549858109237563, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.04563693212632035, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.2616350227334417, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.014935758919429663, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.08106107745254391, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.044304867337633724, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.20806974344498103, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1418524086391329, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.38295770773758747, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.15268019045355535, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.41028757620299977, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.030860166165309233, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.1100250143829584, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.21255327712152144, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.43272151570555034, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17560861603765618, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4284862592126998, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.09632940954518097, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3503787449131298, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.08860973467526746, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3178004360288637, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.034863432218006, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.10898936628924337, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.04181105630729634, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.12631062389493458, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.05918530850500025, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.04695194140007918, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.27375248375511296, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.06609667473412645, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.26197209338359717, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.22815217447604735, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.48973384754323573, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1507980395794452, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4306039128585424, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1438459189500836, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.30693371625402605, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2288990188897003, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.48933901443699584, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.21496499417848794, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4621452070963622, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.04294724676074863, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.26827434375490194, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.009624974244068071, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.07318255686027669, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.043420474648595074, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2884095690753619, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.17382347640129553, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4061580777885601, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.13868172938464635, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3094469764260441, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.10361854845420869, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.32774802711076473, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.15186969315425305, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3458120002305796, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.15514179348953702, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.37626364881514784, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.05109780779294313, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.27453721503960304, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.19074380068002203, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.40566585096277824, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.011099726775956284, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.011099726775956284, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.20031726728306523, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.04846885443759431, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.2058585556849374, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.2518167302716443, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.28020858443704566, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4608753441128863, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.18668631382554257, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4241639400875279, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.20485833586704885, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.468735805943922, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.192481383169461, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3799051443349615, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2191271005227237, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4602679885982292, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.23460587033646188, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.01252735726099625, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.273148644463442, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.09431297723472011, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3616856339096348, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.11091252683001185, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.26607634610445896, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.189717083187238, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.10266747466754884, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3364703638684802, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.15325054291996534, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4125406716806515, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.14974627745213473, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3288440080133683, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.22381487678101888, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5249370100068887, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2284908570852028, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2284908570852028, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.28912109037408523, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.05694565324984518, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.29870977978564917, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2965847839642647, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.22274170049761707, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4532692581443855, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.22670340807570744, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5112287500509207, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.2144604484498437, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.48894052224175993, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.21001173689943997, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.423493931076046, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1819297584528903, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.45996792687703736, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.024019278322400153, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2257355657343791, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.006232910970143225, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.06317168666869727, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.06938388878349923, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3541078046399395, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.14557808399334188, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.36598346755702993, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18154954789336694, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4557483776072868, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.06897533888461813, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.2776666563000344, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.1665765483402476, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4017968725013381, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.10522014436415743, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.32544051539581526, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.13122945980689196, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3219448107305951, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.10666682719585797, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.33462901494141756, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.026001137235511722, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.035471813848611235, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.21230556005755616, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.04151505758906764, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.029020401919028414, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.14829113372489366, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.10367752489302245, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.27027811810666413, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.257476399230248, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4616305811028715, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.21429469817014857, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.48426124503105794, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.12189363728567917, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.37595660827287636, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18926971577178767, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4931453714148122, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.12938967099571722, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4720138889028141, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.02181368760128402, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.17151506368480512, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.004663531624960091, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.07262533604330305, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.037401300306846526, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.27395881217705964, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.16780109158842918, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3968694014697679, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1381751568911733, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3121557499162649, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1579497466001673, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5092928545844059, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.16286876096900815, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3422914837190449, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.24894213883371918, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.40837997135938553, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0985948810698831, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2593923911428194, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.20198948917565754, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.34858221035657466, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.040279344208305194, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.23810512632594893, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.06888992790640074, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2874483621307283, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.10900559073774943, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2863243514773182, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.06584744332862066, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3081739316918366, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.28562106983744195, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4749518446683913, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2500514006614894, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4683806074404792, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1631196072688366, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3502730667074754, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.21286836557101563, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.45055232014427626, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.22138385440094224, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4871238379919067, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.021395721635824105, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.19029771810891044, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.031126201157905466, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.015970144454664378, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.06929847827527827, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.30185194035792856, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.11697642623186386, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.37117753637984835, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.20065115069964384, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4084885616013531, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.17621963873521423, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.09916146090364127, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3121110160693956, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.15634566502258415, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.41100137155785554, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.05658523178050362, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.27543168466680934, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.22669486951066523, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4484451941575473, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.08054298732230164, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.21478595402015604, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.011560595536104562, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.15272161850945196, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3256028391793645, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.25884168663817486, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.28619616266290565, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.509863149159976, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2243415229038419, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.46277723348474986, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.07368089078790738, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.41452613113710224, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17892846390928677, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.47088195615067674, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17121897852515788, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.46387669666892856, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.058474735537506775, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.302418496404915, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.012370537823050053, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.06660321132654005, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.09831093939330879, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.33203866499974327, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.13805615693046389, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.40787998733941394, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.12291219097556666, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3448002180666873, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.17643078314788999, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.40757584786696294, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.1989414239237112, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3791567776918788, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.19473365049885608, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.41698501435299, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.111871161288306, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.30886933073849715, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.09916009482330297, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3032928217006101, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.22001196582907748, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.05095758556418664, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.22156850902870967, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.09453698369211004, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.004225285108890082, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.0861677526401815, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.2894688065678073, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.266802610525441, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4519949729282707, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.17670061747630258, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.392453103603526, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.1995980198896431, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4244503391142409, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.18216362398065106, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.36524832602306334, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.16619218719171422, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.36839901474618886, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.11322415613820716, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.08319287955437346, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.08383676689911676, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.2855329690010324, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.19148282873929853, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4707949702068854, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.20608572305725564, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4704943905570542, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.08183353655679478, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.25007633393249695, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0981642545874085, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.31793222329793575, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.16439209425428677, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4076099284398328, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.008104773738922768, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.07651300648420487, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.09478705591775652, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.33293232395887284, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.02025073422738642, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.18351062254269088, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.03524547085277134, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.15744174434548794, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.11976209355757551, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.27004759126600675, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.05835638675929789, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.26034660656430636, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.18740401341623053, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.47595080320432986, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.18529763041106434, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4741269560545019, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.09142555538569784, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.31371707771405133, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1490232164900303, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.43745835724045856, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.16000199901017287, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.38698876630115175, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2727622868168819, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.005606294971348417, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.06662245090541388, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.12752236829255797, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.12157241570357182, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4080990097991491, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.085416483900781, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.2825804066750608, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.10415298161056984, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.33452632923050557, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.21204239268527586, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3846197304420823, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.18693338154817452, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4290809947421753, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.10793175369072293, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.29660617805108785, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.14057105892389254, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3028381427383384, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.02520941562084078, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.14480208828142038, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.02332084309165125, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.14147721432606347, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.004763623056487517, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.07485928007606017, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.0262417467440806, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.04981477508091101, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3099723997891052, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.26242764207671093, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.48831610046795776, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2697134918431208, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.4954790401096134, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.11689600237805012, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.38258301195690664, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.19809535837880818, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.447539350421338, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.16165276884674076, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.48087204023787744, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.04376773937953893, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.24391688958872212, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.004718557257042585, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.08019304349523304, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.05614653993259943, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.26485323792360876, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.16431887969160053, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4088971379214799, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.11452508920842025, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3212742401272785, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.08218359452575877, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.23905391762860753, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.17673835621668263, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3902085179927465, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.19609395632695717, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4429882447488722, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.12351824822447698, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3906003941586503, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.13635319583999642, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.2850432830231861, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.022084251686401823, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.022084251686401823, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.051272222858601425, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.21925629669878902, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.007327166905859771, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.09881239641706457, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.12403840452736142, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.30367861518441364, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2730720849895809, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4904647237477465, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2733762611506788, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5386988475624784, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.20362195873137665, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4504603915919526, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.20927351091825444, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.41232284529686536, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24513601438741284, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5084285210448447, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.05885295453595563, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.2979167122026919, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.006488743008712295, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.056679733231823716, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.04209313835422283, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.26913406771501547, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.15184278721506198, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4093399937921707, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.15478222669012726, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3550584759508654, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.06244445123318812, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.28239834932587327, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.15685632649880807, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.34378295878971765, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08266931651605855, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.31275119210218016, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.04731666745775026, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.263716605484278, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.06070088845782673, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2584364364927186, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2290266995057779, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.19149954206308856, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.06467646497347093, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2374647159547877, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.05821399139564002, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2556606247641527, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.06105309074409913, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.31300959355700714, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21356649685679252, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4243725761948095, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.18755123479604602, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4299642051662849, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.05675489168243481, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3098329822024127, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.14459834065375157, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4652483976219767, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.16524575790277993, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4729546491009478, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.06544042341813289, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.056417721736162135, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.14707146406788849, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.050577564370191244, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.26455598459911367, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.16758563722627876, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4598125962895632, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.07875433150726119, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2638954513805452, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.12334630141873701, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3570869171580578, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.19153195331287226, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4035796398628449, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.19790095860977636, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.46847710246157187, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.13346878790838718, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.30809134673210076, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1054433514098504, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2840946641780818, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.06071575852216007, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2149299083218784, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.018778588483215123, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.13941904818883186, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.005649824351905227, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.09384599631616997, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.042575418285137674, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.05179431911506798, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.048025713860174464, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.24286102972715728, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.26356108382670784, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.47640029725892175, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.281597136729422, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5252125986152518, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1738582449442553, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.40161714405254456, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.16120676251405475, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3934823211441987, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.23217334003519086, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4674701273842459, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.06367770924275107, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.006102253115653432, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.08614490649176082, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.05052791122570277, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.25244788085139286, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.18041700926694673, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.43852448917973136, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.10734088848154077, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.33946796348247366, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.12499287263993265, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3031531068573407, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.14318317227039934, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.356756117753337, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.195067244269841, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.44793788693902575, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.059890467169145326, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.2852233544262429, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.12768613576122964, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3279857505284436, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.10654094597354213, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.04558952792664619, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.2502391728166904, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.05915285533036862, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.010570499657301486, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.11006734435626991, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.09486000320952537, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.35631854924113476, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2529913062741307, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5047314299093542, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.19151044656734614, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4810197053736848, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.15720527174368754, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4715103005986015, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1853793533058344, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.47839321418703307, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.20499701307081308, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.48187091128254506, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.26559916879276785, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.21349841283886073, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.27204846616025496, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.15197436941722972, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.37271000364127155, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.17795920517030017, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.41862955401967455, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.17060644184287996, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4054584763100862, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.17670199390439656, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.36682227371085463, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.12662807666447004, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3421762778593668, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.11509582662256548, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2567415288537121, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.16136987880724096, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.33626920748765377, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.09630909369886713, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2559618634215989, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.07924178226890699, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.22062584481281217, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.05468777721214362, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2495519218392036, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.09527579368424423, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0691791023737071, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.33564860418725057, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2700569573710134, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4456029881233736, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.19319119695627468, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4018622995178534, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.2195372587354865, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3664303672465512, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.17524367912943578, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3908643084796051, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.160280283995202, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4076009931283521, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.047088289574980104, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.25195062605509155, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.018807992767181335, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.0887797545718027, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.06437840881729344, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.26576141148273813, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.20266988583156875, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.48179719155586864, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.19388048412249795, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.44361702376789247, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.051668546856871944, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.30087455074312014, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.07523788658275522, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2771251147123664, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.14016000761839026, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3800106321723014, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.09979289495211781, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.300593829152537, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.13230039635238258, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3269392904147474, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.1404951243925061, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.04003396689595419, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.21079478437872567, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.11588911231177465, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.23827009172444413, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.08246064965255168, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.245661992894089, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.05599772899587482, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.318436522842419, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3010169295163665, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.48601931182953334, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.22778648697249887, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.44620122478414426, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.14947301772770566, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.30933819017694797, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.30287590293584354, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5604725285592409, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.24773192469144745, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.41931636733206046, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.1274094829338224, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.004712897582765101, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.06896759630799948, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.05079616735013072, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.31593754046223704, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.17337747588904887, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3602154895924569, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1237012344369667, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.33331866832253354, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.13636398180563136, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.28987182748753165, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.11209730709870733, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.31364540519664647, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.23687866002887717, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.38411414840380576, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.03153454293495729, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.19644459003645154, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.17544176680792672, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3246583081139427, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.021430138391124044, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.021430138391124044, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.08369831431112969, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.13458070775959802, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.30027380966184836, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.10145234629077284, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3610324630960452, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3149975098608352, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4828711196365768, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.20669234829120028, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.39548218036437177, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1955903221252232, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.40982133788576824, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.15417968758527056, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.37529479808790556, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.13326781658444442, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3502365985083862, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.057951298400924244, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.25485985066179334, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.04130329986722028, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.041010356073949844, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.2740873282030685, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.20923298022634812, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4391664941823773, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.15589802574348086, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.37894206802233305, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.15697021945336284, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3714913924449907, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.10748431441036872, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3292908634814674, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.13279543122431423, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.41564365771461, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.010711907071897552, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.09374809941236832, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.09199306870423013, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.22163854171424513, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.011817365490829785, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.08595451843343337, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.010616420495610124, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.1084362918047719, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.005478181714811864, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.10269142826924012, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.04059965052015497, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.05185187637560759, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.08938592536025085, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2237243844850531, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.23349229612349748, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4473828787417339, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2565364020841773, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.450805390345959, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.12201642745653093, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.36024578318571476, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1107058214411635, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3732245061642063, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.15069183256176744, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.40277025180754966, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.047451030956212996, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2751988338212752, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.039842290129399376, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.0904612219823137, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1049798504546962, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.35536862718638546, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.13303798096767047, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3647236067340644, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1948502778967486, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.35525815981538433, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12370396553485627, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.36583052207842287, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2119411486498165, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.43506560274344996, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1998886980070848, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.480958678209464, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.07330323852439774, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3393411295283515, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.06089987261870556, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2933161562815446, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.19842901779549207, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2713368244937688, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.08430389952515091, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.0415140550178777, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.052809267538197285, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2937198064881724, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.27439824630186443, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5150965593614537, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.24133620987777477, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.511932195436477, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2024418414576267, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.356433349373201, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.26748241941426637, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4950459974606264, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.17121897852515788, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4511162476169617, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.09796172813331827, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.010814656004254549, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.0896887156447935, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2679540690980116, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1769688060281599, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.43047038034793145, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1618333627385132, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3458746996740858, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.17740552204949464, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.41741195239753426, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1442495030513253, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3320792016461631, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1864648050279449, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3847069310448368, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.11307485585998263, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3059738530196213, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.14391826157279944, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3239832814361818, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.13774913339477518, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.07000554934826074, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2193270198435431, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10022078146902932, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.25434273119344186, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.04870160687070819, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2290700851514103, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10450731677295656, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.37394939751177847, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.21973252102999322, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.41512397913463883, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.19111021356168978, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.41719140749889133, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.15991026977564765, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3236465324693797, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1668854639288255, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.42010321376888254, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2384674585580613, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4770811353427645, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.04614982002370652, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.27126718818718293, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.05135254464623785, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10818248451466282, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3258308765385693, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.171833798351082, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4265037420578645, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17393111207515277, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.39042812195808824, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.14437570687117765, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3403124594589958, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.20204254060396054, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.40631134079482684, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.09215607021469929, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3442184231768954, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0653324228887703, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.29791150536969546, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.10027955093430833, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3650503321876689, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0344468040504092, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.20160402357264132, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.23784721286689645, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.020318277383243454, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.08661842632019902, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2474248849374247, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.045518360152495066, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2398899448049606, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.453993856664573, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.20217554656803474, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.48992480826449836, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.12853443501376743, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3781656409614192, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2009118875039034, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.48691094449139866, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.24551993304721983, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4695982872144731, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.044477892435255344, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.311934411870309, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.00517631148112868, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.06740002819965461, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2452462470568165, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.22922072303609867, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5075702211165173, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.19064689695123957, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.36954921822756504, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.19591250914526429, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4012747453552514, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14508364614975736, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.31907461937638537, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.22110615989317936, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.40753699277004807, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14346715239003294, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2981447906678646, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.15998665872195003, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.35681333217176553, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.08600488468756139, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.11933855307350258, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.07534587005281039, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.04606011483185924, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.05077972802413032, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.044154894914459994, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.05077972802413032, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2916500733546219, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5172529356293942, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1907614927330316, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4483545139496048, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.24024632160930773, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4371716158103883, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.22508089265035264, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4850615114261917, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.15188475622796066, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4050868631852785, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.06951312155807014, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.11472913879621423, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0484266906744459, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.24913886287924247, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.11397867508647329, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4390501380282409, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.1785851272602057, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3800733399524004, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.10927209083864609, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3154924313217727, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.14399622191067446, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40927634117587713, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.08670431063422109, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3440590449655204, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2561794438004549, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3141794892548087, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.1786034620524431, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.21970680195024106, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.04825170735480719, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2469647404663632, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.018801687736883517, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.07620759150236847, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.03529712519454766, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.181042027648149, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40879266567927514, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.13932127331731958, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3737850640861325, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.13077065491742576, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3664151599144951, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0984296905675516, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3288790320536164, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0968035844762605, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3901340721283281, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2599817969196305, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.004333829482338306, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.08668716511436675, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.082669215590649, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2792157437153376, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.18851320324917495, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4118109845203767, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.20113943179758872, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5054929215592371, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.12371001489967776, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.35233081465372856, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.14334269972024394, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.31813833621829557, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.17921007574834458, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4219795466326858, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.02606447183652908, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.20219794591777904, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4267163836239083, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.029248290291042138, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.1718027364322228, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.04766862058769161, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.2043794633423878, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.03336328330137746, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.1957772364958447, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.041963867461860996, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.0516224121615006, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.30809284179770613, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5212036360075764, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2465035340121816, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.45633441623452936, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.14044205071392263, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.38712210510627154, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.27182145159884086, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.526070184366635, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.23498807624250856, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.48765523434090247, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.14416088697983637, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.019129282930908934, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.07711027977872816, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0957971819913436, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.29031027439121476, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.06638301361073934, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.33617826818768626, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.07088281524771703, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.1725752257112697, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.11414041086884202, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.35006273110713093, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1313979824300913, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.349118229304567, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1927225490012646, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4132550155072071, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.14857103353932644, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.291239957190704, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.16558784557611658, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4099467657500184, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.01786532108380904, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.13121577813207103, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.05489691210701318, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.23494793085665383, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.22432434110392951, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.07275467861454202, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.14614295662986437, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3552926382379845, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1949241563385421, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3964264382707378, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.209649431441878, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.46764621241357657, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.14067214182271884, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3683127018431368, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.261537968195518, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4670896511609081, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.16432871779782451, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3743841843286974, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.043671403238541344, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.25919035356327436, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.009837503470338078, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.07381634573546925, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.040393483260585776, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.266056205197059, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.23272041020266335, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5347837552430531, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.11901413329120636, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.2908877283991857, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.07103656838719773, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.27534420196130394, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.13329630208389306, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.326901495019388, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.18044662621032556, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4057030488136589, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.17626315276087934, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3402055671772128, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.09337623404557584, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.255517984683644, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.041301896522444675, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.17385088745134245, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.038390108835707044, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.21229342933137452, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.08474505774044223, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.253832017325449, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.04460344454473387, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.050946055101903635, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.055710421288008224, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.23427034762899968, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.30658949507361904, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5157122183970266, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3193100500854345, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5162296859807791, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.17957474071770196, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3714895660565911, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.17878846497211381, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4805877835621217, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1604142113422276, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4821009866720967, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.025349142884759417, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.19474598217933617, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.021888464288139578, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.06880194424178804, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.07403099975997424, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.25305896973942904, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.15964995175974525, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3581305879558541, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.15593857496482408, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3832822126692406, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.03964626561854378, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.16338514690556735, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.056046675552729554, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.18841684806509754, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.209649431441878, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3690324235282993, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.028775739564490036, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.11889226114628741, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.27239589447707985, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.05973439570871991, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.20910579957872127, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.03133618553613538, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.1568404935147634, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0103535778609182, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.1374348609613479, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.08696621894928246, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2942577140950735, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.14094927983933814, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.32113486843339634, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.19139210005771193, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.39990366323430515, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.16166102253231274, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3131370145851093, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.14834005339736556, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3650996903674865, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.19730454275995257, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4060233750197503, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.20908195213737235, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.42477137691772376, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.06349176246319257, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.06643196929197938, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.08968389355416555, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.26065548087048496, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.14086598242600956, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.36137008859982034, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.21107720643690867, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.43911506176829573, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.03937709136327999, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.15616761711166294, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.12066885519467463, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2616326726997023, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.13596145670351717, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2880980104507562, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.05508931511949558, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2517305146500679, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1101341452220285, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.27185902677547247, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.21712215954833947, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2399710396553458, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.05438497632520132, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.22483031146316076, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.01465842448246531, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.07372863328844016, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.30760942657718227, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.22771052484743856, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.39452182489614496, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.18493395776181829, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4386240113678834, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.20352428331068037, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4163814361305384, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.152083233596389, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.307389858154115, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.23982122784780777, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4312572299745367, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.12388166705800276, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.0019267822736030833, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2729231212296316, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.16084008820568224, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.49453446122836875, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.13827947882974537, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4010585707766239, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.25209019490063744, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.21271493861618962, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.48032757836964046, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.10555548503828743, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3698372209729681, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.14160083166193357, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.42086810781344214, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.15873502699291203, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.37163016195847015, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.03225234735559956, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.18669341091479777, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.22123617047892138, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.13242778128862073, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.03706945858003643, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.10714846237317564, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.23712734125066068, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4737847575052381, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.20923986420852636, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.49694187999493455, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.22218345206036327, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.531967559614025, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.24660313247404905, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4750802403221604, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.2302979641212271, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4950725740253287, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.03573716512983384, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2636286370686069, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.008808482479470064, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.08172375369450574, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.027855314822211794, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2743064672346355, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1605078796467662, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3607284417441162, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.054452721416611755, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.17786113214625052, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.07394430141087438, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.308455636822965, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1462174255670787, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.33477501662684966, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1608187789877052, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3641324834231433, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.07353968474801274, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.32309698978167023, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1046814649445003, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.35929100435813716, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2108920708499109, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.08862461368125828, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.06361340947543563, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.23606133878828675, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.03496289474177452, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.08333947754529797, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2642890052611854, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2009233547607218, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4134068926197593, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.15677826168589556, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.377185194614394, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.055923960513901805, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.19457014898752104, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.23365039523187425, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.42556791226379487, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.21927506735329194, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4315395376333666, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.1373600644267889, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.006313131313131313, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3270101704079343, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.25513503948815797, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.5313546358608554, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.13788203160207568, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3107655646435926, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.1709984622318412, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15045845033645844, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.35967967969652714, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15055407617907607, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2925093305055971, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.154484521805181, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3359460432439711, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.12832094336767122, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3205905925059277, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.12963772036574467, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.06431520707014032, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.24869345184740724, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.05137179048809052, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2179007767607974, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.048398308556049596, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.16446970798512367, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.1688821792911141, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1556988827286413, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.37169558531876135, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2140902772642263, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.42684341080390703, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.17526461622814685, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3887795637263755, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20843200459956857, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.42187376156085354, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.22441108116111003, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4354495412786265, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.09250654988890523, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.060410667564482795, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.04978921592425999, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2697504713353615, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1634286453435278, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3969874268891194, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.19418939219609221, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3901489832573322, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.048304077864023846, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.23970159686687842, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20653927241974365, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3737641013916679, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1930726574453761, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.36015092354060324, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.13575658061231063, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.28640162384542756, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.11215442765734894, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.31037546676327293, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.10988528279333451, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.10471517551249318, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.08226969152601427, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.15696885690938372, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.05196767194788297, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.21653643432750053, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20927351091825444, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3903841356584215, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20345556664614994, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3922452261221421, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1872830229239533, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3677267744209934, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.13963559400140405, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.358561623108295, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.20899938247825522, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.41457588389231614, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.04191056758684487, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2747808392885938, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.07846319110079712, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.11613581491070282, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2960371403891785, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1945423193070673, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4706222268986097, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2080824447945289, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4427653693519822, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.096873931674983, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.357921862131455, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.11119610005454576, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.30792475044662354, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1321058295592534, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4148432475461046, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.08720698093571426, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3394300386679635, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.10180741374280794, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.35728563956947634, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.06194295956144168, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2317557084334835, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.035176121652651195, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.17161490917675337, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.07130512646301328, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0583085961396453, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.24750289066642356, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.08557431032059788, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3075931534356484, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.26485344282248025, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.49926833940150855, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.19756811204569283, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4789887223696734, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.10226015509299118, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.40597878858272624, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.17770686403077657, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.48140657517707824, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.16599660185655377, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4490603860832405, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.226528380402223, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.06004443343680894, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2456391015238017, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.04398085473438986, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2975413849030591, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1334077033965181, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3538599860218621, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.12768405545127823, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.27604666315815635, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0780295493314355, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.24395345082956324, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.08696621894928246, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1961381404046578, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.10537687828190058, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3233296514764708, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07541784671250895, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.24910063520652925, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.06928783103636403, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.28222804846457444, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.017901241645426468, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.19675187530586138, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.032083175467215015, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1187504033570596, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.006322585449419441, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.06296222300910888, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.04661045606865638, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.051225703208053745, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.16491845920935155, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.2549048589985116, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.473197481249297, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.20050198179023138, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.35990851497839205, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07176020589506472, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.298641857962305, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.12417300961365357, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.34447336960471725, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09985998421086474, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.28957013810992877, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.08690271774962008, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2881002270580955, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.01552617838217617, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.09140076236425068, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09225450507547597, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.25320206287790814, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.15757286670204007, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3806769190392542, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.05441383188454176, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.24018232621879906, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.1426986810099998, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.31786120425004616, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.20406556965912795, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.37608957302795537, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.12961716938790843, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3033295224621767, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.044505549603083075, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.24454668865020499, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.15282474172999858, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3332497402594901, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.06299746467448508, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.07142051780137347, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.21559762402820992, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.05462016386637322, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.1059992243305236, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.19829657978768986, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.20796615419937428, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4053550762669065, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.03184787808073657, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.01699912141808354, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.18085489460790177, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3621070250317998, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17617182067763734, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3491313268402431, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.19992549928415637, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.34245426295474757, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.17229614610286134, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.07124457091987033, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.19364253421963298, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.35262250988466515, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.598931508663349, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.7353063745802827, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.30677064886592076, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5308555945242818, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1327526847508867, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.37850602486495205, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.18405035438430847, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4142901090120915, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3381363585599571, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.11719733243527225, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4023449434976014, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.13410301071131794, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3942932268034351, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.11625490582216925, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3649888937995206, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.11625490582216925, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3649888937995206, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.24239458593560292, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.32069132319909655, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.48514659426076356, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.605169324059723, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.08852681798207009, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3583179111355935, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.47039611627724026, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6298835480734482, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.5920893212447781, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.6925021521158101, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.22478613858269392, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.44348101018104913, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.4026159305424288, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5712560131047175, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.2296660762967038, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3916051272553242, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.07771324020744104, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.28137484554214276, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.183687049781416, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.351911486970854, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5181825846579515, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.4262221594184117, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5886657414856064, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.286608441075188, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4579283646292802, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.25861130592298187, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.39452644092432093, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.20379250618355427, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.41085414309816914, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.16913268830937947, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.24522672479887386, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17328174803055044, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3178268797869574, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.1715979984488091, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.1715979984488091, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.2990226215771518, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.4323734152924571, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.43218646131638366, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5429193883657468, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2334787866969297, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.44212827861876997, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5843055590705747, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.46269559069048716, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.46872641361415845, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10434360980785336, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3012789660952507, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17248715680799764, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.40043565243219187, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.422575783710386, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.5948022735911326, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1518079711528412, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.35052882681128233, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.13835317113453516, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.16343842313572918, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3986641525285075, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43186481103649477, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5792139686527714, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30890092021323623, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5553909583113487, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30890092021323623, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5553909583113487, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.25798723088167685, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5244854229988815, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30890092021323623, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5553909583113487, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30890092021323623, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5676965183365866, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.3315037521841549, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.468197879470805, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2003825042083558, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4389344981392915, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2003825042083558, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4389344981392915, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.460474309246715, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.6213537794704693, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43104530127419294, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5857650290593939, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30829623633682235, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.44487288478084186, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43186481103649477, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5834549494301647, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43186481103649477, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5834549494301647, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30890092021323623, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5676965183365866, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43186481103649477, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5834549494301647, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1577724877619984, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.41413383653794145, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.003172770121174655, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.43186481103649477, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.5834549494301647, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.46092611919700416, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.6365915338629015, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1690979933029136, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3751861276375209, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3344305108778801, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.37017501464955627, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.22830327153687363, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4341368544819458, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.23874935220945062, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4641140866580373, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.22218130727359342, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.39929356245904674, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.14646977906722897, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3483313798210466, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.14646977906722897, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3620367958150382, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.3194331635465395, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5031092445628172, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.40604669782469155, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5425760820715552, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.22259002746653545, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4094746713677566, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5831913487431972, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.42171123717273484, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.588496189746877, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.334422418242443, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.47577086062579566, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4482907809719588, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5498272118133005, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.4180999216775964, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.5354721595275848, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3786410842846065, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.02467424260792568, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.21902340561392236, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.43906671679239717, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.5234484809182233, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6658297773613274, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2840563956846642, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5110250591004448, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.30007504691018483, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5153810823423555, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.14074957769288798, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3750035199199742, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2543269102041851, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.48299470788082083, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2305720744624697, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4655848022427904, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.26538706048179084, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4982627378595717, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.10951170280696113, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.2749574296951936, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.112289032173749, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.36102352464840753, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.232738415750697, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.49618971681248764, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4569234874515144, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.6188845588287419, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.09583427356739785, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.40272844461027313, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.45479124441660884, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5872444902217987, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.4036650481496061, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.596979347591019, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.3488611533620711, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5550499651473632, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.31883477089875656, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5510450101159524, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.32808594346681713, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.541693039806838, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.006356168623193365, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.038236956722392024, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.31998097041178836, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3815250264738168, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6516314751979607, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.19920413481788912, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.42537796926163113, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.189902924205034, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4072184389907138, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18710260593933364, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.44334313717706003, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.20498415630763028, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.41559166314823337, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.20498415630763028, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.41559166314823337, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.15161074985415177, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3796830006266126, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.09327870647412652, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3735036941607298, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.09327870647412652, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3735036941607298, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.07757069009917116, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3253161209971999, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.3611133026003336, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.628939204695425, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2445648178607759, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.533167536340577, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.6607380945724757, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.26385937298217066, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.49313681898117245, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.22168992033645996, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.523689661176845, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2722704374402053, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.596004654894533, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.2779440822726561, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4935559299167756, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.20711956213739935, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4163963687531719, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.01008902035184167, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.10279947040838337, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3569840483632983, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.40003810431098236, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5899097408105687, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.20401796878756984, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.43317630453631556, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2097387761551816, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.49663301508497226, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.27067168022307464, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5439625482235064, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.3337338878596308, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5500899219967885, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.40066361284662694, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5020331850026643, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.18679710353734788, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3876457319870774, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.1353358401115373, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.39493151971582074, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.13534889927489716, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.39100244531038747, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.2826204057042236, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5043062352893725, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4329476703214299, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5804967339644117, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3714562234354218, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.36330554542576643, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5680915937757648, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.36330554542576643, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5680915937757648, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.29588994069727786, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5527117669081858, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.46732353406180216, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6059276585345114, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.4348120146318404, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.6115466077533132, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17997291109158148, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3492017591855697, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.06266083709457643, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.36565527196849945, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4882803186347697, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.38047531731529327, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.49485723102957346, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2044887070217883, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.38471585132587544, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2309552734743087, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4672309378181727, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.29886658673327365, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3270607740380116, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.18485608959451436, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.21812881407613688, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3598346059855135, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.24425230015000562, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.12137360695980427, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.30236214151783924, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.1367498402979849, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3943841419148219, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.38086548136555726, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4893838263924812, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.22454147741956867, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.3890858187033785, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.517430128986546, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.4488802814935875, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5347582736861126, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.5676006714726635, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.6880701448812352, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2974074484950165, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.5121581247515657, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.45479124441660884, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.588444085222193, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.20438008283049838, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.010162846529607748, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.21947959999379651, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3226457008913864, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4489235959690452, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5934678825154104, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2980504190448601, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5101268920225042, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.28800869328515505, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.49348678623542436, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.2429163097293302, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5044329486461447, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3205104057171838, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5848707979780723, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3026681380066168, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.492659495510912, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.24586918158076287, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4658595745396681, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3319782560727053, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3319782560727053, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.23073085454808062, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.44142087654422146, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.43186481103649477, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5449210171662631, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.015895766317321515, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.43218646131638366, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5402913319043152, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4488802814935875, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5896924236258139, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4406612884550454, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5676112112992767, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.4476950425126913, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.5932980209045412, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.47232136380051687, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.6260769803555924, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.11719733243527225, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.311874117016478, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.1483315516064897, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.25249051585915977, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.38558450790399557, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.46832763312452297, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8176110134774669, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.9436043261706615, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9880191679951993, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.0067104198717751464, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.9025232868361638, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9169897590736298, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.9234732618882052, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9472986863542112, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.9709835434146469, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9951728990866464, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.9154051169199643, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9757471794927451, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.9154051169199643, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9757471794927451, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.4888436840107989, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.8291158208899767, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.8935248372106969, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.9404428602061264, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3642482472579296, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5342538783335161, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.18831933500600306, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4318025704181776, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.4439623527529193, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5309137918519957, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.2628849077177109, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2375594795209403, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4291541972877265, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.34613789243685805, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.49330323192607783, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.21039673882735752, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3872019296036794, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.35419471368515315, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.35590473147868196, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.17879309995151985, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.2568045428196672, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3282410731566718, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4364543652558664, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3715102500248764, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.43218646131638366, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5369715393520321, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.5492014936877967, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5685465222735583, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.6099084961389527, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.658015760514539, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2464380578618272, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4278399263644655, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2699951684630893, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4217192983941685, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2292375926648613, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.45134534124852044, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.1879604201975219, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.11956615218925931, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3305337714496588, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.28406136898728457, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5649283064490618, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.21544027588567594, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.5040038440508637, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.28552127890094825, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.16448947606185552, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.23644551786043141, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.30630098078522544, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.506196410096354, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.3395693620772222, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.14494568696092858, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2628972098240789, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.14494568696092858, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2628972098240789, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.11823053204772466, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.24615921057796505, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.08463566423313937, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.1696081888168728, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.09184122179650878, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.20224830805167826, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.4955056754877292, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6304896503844739, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.5038374191720147, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.6024265863535287, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.3491726680217181, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4946434087697324, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.22916123454514536, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.4192305796685782, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.26871275285988894, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.43155016612001146, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.18067521624740268, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.03586767012087445, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.10393938326032184, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.33864898055191395, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.23843418577408987, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4082320855803597, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.26970223719007375, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5172978597562362, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.2372622545962587, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.49004864454711367, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.190140357671548, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.26802811732881265, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.47842918615794633, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.16776974914462364, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.39918336227233053, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.22556860731509948, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4747086049005634, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.08950723402647723, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.33168942069142754, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.15013907175244498, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.30693889771704796, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.23647235972003527, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.41650969469918997, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.3456747067447366, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5098918117126965, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.22311931550349762, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.4067965564160296, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5347497635970215, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.37720172106772915, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5281246430019316, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.42662911848025076, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.5800596652250789, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.39420326688847324, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.6371076304605184, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.31833550883682055, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.505309837398544, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.057821363839455714, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.030501743754356173, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.19352792845274666, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3925864519770825, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.49458876622696707, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6179893617801274, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.30630098078522544, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5439056051092116, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.3059872016765634, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5499457869553984, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.20076347441707354, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.49625515445592083, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.35013594820721267, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6055612825349426, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.33626819961829335, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5531226519754557, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.25449674462950855, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.44805409822643144, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.11912215481390381, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.27872651214887206, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.11912215481390381, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.27872651214887206, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.18665948437666813, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4437597552815582, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4644593897211701, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5796009653873663, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.1927932674702769, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.5004894768464765, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6103735933609515, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.490343068868897, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.536581249889066, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.48670274592792, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.6717971788322309, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.417372155782838, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5043502592801646, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.4843150498645881, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.5578850047683247, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3374197535175977, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.06680433144407034, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.2919280798407827, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4076170046499833, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.41520313827696, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6485212540886613, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.19850842371858787, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.43584341835040474, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.284161309400485, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5096201523229312, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.1134451991138546, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4186167762559285, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.17251155106930158, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.331584914092895, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3228858965814099, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4495802766763041, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.3312570339636223, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.45442661484375735, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.19397810500627852, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.21990266141251047, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.24088562704853508, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3796021685415706, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.487233540201337, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.6075898035634494, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.23440876674515643, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.4317853842116786, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5396321094501078, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.479676449968321, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5540737713291652, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.43874832905672956, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.5882858748700781, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.3270207865532903, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.20934077434952414, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.44095319717043774, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.08298317943887776, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.25735819287934475, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.006769280526888359, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.35465713644381464, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.4911561718424494, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.37233302529431345, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5112697990822607, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.20170335119323748, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3541251997977811, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.20170335119323748, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3885781003640365, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.19139378056089276, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4390566098420477, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3530697921185709, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.21741853044139284, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4000689216320657, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.22744906705116497, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.11460773731685357, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2063706369833672, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.11460773731685357, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2063706369833672, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.20533223830207933, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3692051451450368, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4798870804700399, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.190947150655844, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.4946630566933846, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.6169269421105686, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.4245848004818514, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5212978747333228, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.28392242834976933, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5447934365522582, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.21644298243944068, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.39638009285990555, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.18043239916836057, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.28005066200532414, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.17657522592016398, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.0013316837154984055, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.16192940337079562, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2536107727939302, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3857901147929391, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4926358895461277, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.10508106635796587, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3182774828667731, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1214053825777097, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.30188342402741686, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.19420534060688366, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3642322841308566, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.09829979956341456, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.2894553915787499, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.10355978106869969, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3008852578497809, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.16542259679471108, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.26975832150444645, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.08700223397019134, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.23602944119319944, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.08709145169981267, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.22981857327949462, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.307338019036143, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.3701729257793468, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.4863138218190477, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.17278555874883156, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.4407883467611227, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5281354273455451, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2945667423247454, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3820111377308234, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.34848192645275233, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.5640398262082806, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2834052290575623, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3513608621054937, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.260711748598298, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3452976012025067, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.18058381042434055, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.008037190855333259, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.09960206740894453, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.23680099011195122, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.16885023000999705, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3897135623573608, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2309552734743087, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.43975656978777905, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.21883928293594496, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4140411856219547, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.14270596284245182, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2812419410574613, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.3060434879538489, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5282587183958382, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2309552734743087, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4513778135765214, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2831988281847858, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.10556805829966062, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.10531631261880914, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.08966592262979808, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.15649677978231225, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.3589732342308518, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4090747564330368, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.10290348648040436, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.16608616831326783, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.45739385800652627, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.6041597507917782, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.4488802814935875, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5304323627982885, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.39448834349896583, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5955979870734485, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.38006094126945456, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4952333573221428, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.38078351880531736, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.5299172059880028, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.20371573027248793, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.08451648022462464, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1919704825961155, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3465066144910527, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3325026294099889, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.45805631044287126, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.23530033724858213, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.46208607300298377, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2936164862319274, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.20512476044697742, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.41887716212519804, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.2835933397340195, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.46818740249280866, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.30644785825458964, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5424888571764713, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.21877512875558908, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.46843499948065653, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1385105944861409, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.29611042850691843, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1385105944861409, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.29611042850691843, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3001327916132617, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3729157997624686, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.3688020573465489, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4388306821010023, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.18196604681759276, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.42984707831776175, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5723546698439199, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.40002626793346735, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.4958139678349833, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.364475284252601, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5303078856093503, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.40570535345933584, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5128999889612808, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.4574297382369073, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.5652380318903051, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1754880585752024, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3605361466369401, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.03788280195139692, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.18426708758406696, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.28632666167603604, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.4824794737945071, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6479459161283603, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.37284027455688556, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5528347504734102, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2699951684630893, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.48283570465443887, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.37458689678657137, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5282052116558258, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.39433348616404007, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5908849928331047, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1945786954763366, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4234025088421468, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1759696284842668, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.40989005404786566, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.20970020184997046, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.35879263764337227, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2738643930663906, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4248517359969422, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.18272411487051296, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.31610070189880046, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.6288402958621878, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.7096134366313045, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.17421986341870865, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.36042242462534135, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.5104779149627351, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6193632913540729, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.4631700687380434, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5656836354906846, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.5368572660911874, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6191297828676535, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.524685968336986, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.6168947391572741, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.37578617319428625, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.5516093876511039, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.10653688743388451, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3550283416692892, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.007563050858412507, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.3245592826703331, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.4961612243992949, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4656455050518963, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5477103600632085, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2887308472548599, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.38846174119508314, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.13497849469044018, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.294518464464907, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.09207365845406566, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.2745662608288741, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.15725970843587567, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3365623219226185, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.112289032173749, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.29441273828339526, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.14722675403683808, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.28846790344058515, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.08940730360097038, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.26833398639382844, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0795871931195481, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.25643127123309173, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.21555651352032254, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.36232263841752405, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5115662303301365, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.18623668314243821, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4478710142948761, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5290749755361062, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.4407883467611227, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5398405650971414, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3325507240998139, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4074972493988868, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.35372399264817345, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4415325921468054, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.428462689716825, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5332275836967743, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.0061376873624774606, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.17383350569405645, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.18154339087127422, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.32445288009194484, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.485644095022506, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5923993450097689, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.15487293534817623, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.39293494862736383, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2746536544630471, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5102501783603998, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.18154339087127422, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3913469689541562, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.30144001884264643, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.558144752753198, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.24364194228502442, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4803275525344554, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2542828011834812, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4695941026465371, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1449700553672855, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.34437317656055844, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1449700553672855, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.34437317656055844, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.33281148468111865, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4458341777155295, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3754361563303205, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5175586680476801, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2864399964630773, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.41837414564770586, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5788593226912069, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.522758369357291, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.6580868319953985, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3876366843353173, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.49788350946214466, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.43024400109694355, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5419412911283815, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3968427844730261, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.5690871427032166, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14331804860578803, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3550333934998914, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.00801785790731701, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.09885362316286796, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2922887728653336, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3150760288937462, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4551575101683354, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.21741853044139284, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3535910166292039, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22171131219306292, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3447082086936202, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2006070365475092, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.35578462620981843, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2673037872588226, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.21883928293594496, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.46862000983867247, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.19659284558894802, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3439604955527307, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.260782501330073, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.2618919102735007, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.21812881407613688, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.30905257672100556, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3492507317994466, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5496225090740923, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.22497847412371205, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.4532607978893934, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.6057637451772937, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.49132510881927216, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.5226059543423672, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.07757069009917116, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.349379547582856, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.30548599245666574, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4679798467191344, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.15371120555586323, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.32771358491396213, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.23316370248970017, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4272786682396427, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.014790009967292654, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.1352102459252932, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.32096940912916827, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.6485902560215636, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.7627201392474565, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.33626819961829335, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5466581859383387, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.4947540498519851, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6678485036966576, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.13753714471937797, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.47439937147594774, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.354358992866224, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5568265126063136, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.3232764601772692, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.543101366143636, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.5046613014990851, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6377969619576389, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.17864866390812006, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.4318546655126832, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1810425767465413, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.40093391879422285, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.5037566723027213, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6887059730011686, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.4334785460773371, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6277016493301685, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3830039704696561, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.42376138127386387, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.5866233345526405, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.5594129511963761, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6536638088389861, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.5639943531321595, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.6640560919035684, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.6878626650756018, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.8027840472006857, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.588501779106902, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.737119524432872, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.2572812062773994, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.47123700535107493, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.009344129172007202, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.25070100037410625, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.41914475317559957, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.38713346831820944, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5376493568188783, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.32000331642122953, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5480591855923784, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.20926433421787555, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4046472012888725, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.15758218479424427, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2152072672209918, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4179680482018134, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.19951297936500814, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3959122807457787, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.20326213373677707, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4211311971791892, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.12966020590511304, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4080786465652843, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.32499291864289587, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3026681380066168, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4321096865782781, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.3484636843276892, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4951272293367317, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.27498661924425016, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.31465871983706517, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4839658797050458, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2983588344542972, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4730509519236799, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.4096636841225722, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.5278686169310903, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.29040471938315554, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4617994565642428, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.23989822204325809, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4111447629542612, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.17659857710927052, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.372208073712156, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.16484140461834484, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.21181203648983093, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.4245081340557523, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2478022357548686, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.49124012500448727, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.21132630077912357, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4175670766052166, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.22554684328666952, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4891635965943922, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.1370370495710889, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2292375926648613, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.402538938764116, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.22554684328666952, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.39468338688472576, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.12890680068769322, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.18398927158547232, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.15865104842499722, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.08013992490936363, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.1552012946702491, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.08308205615346906, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.1560179649845262, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.11534301373879766, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4347773475385108, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5763413809903908, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.4417179753220019, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5530863243539881, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.30027814350488985, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4842037100625574, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.20881729496822948, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3442652041844856, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.13481878804182895, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.20079789489773447, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.34136152610418546, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.14470626861490504, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.2566358039205211, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.5543498698280007, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.7016802877815009, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.13108369255325433, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3929302741911199, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.36484904083194636, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.568282580396246, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.17997291109158148, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.41721274496653427, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2543023714256286, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.47904043667177454, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.2738379692102183, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.48783795879618724, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.14440270272056518, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3829771215415724, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2071380876663193, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2071380876663193, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.16912873274521933, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4587620543754354, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.4569234874515144, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6188845588287419, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.22035958513840823, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.4955056754877292, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.6373668822547183, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.404949394786753, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5523097163463507, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.17864866390812006, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.4085144222648808, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.4333488014632613, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.5965589158023283, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.5004894768464765, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.636358789468443, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.006245016945470881, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.009743563745649522, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.31745891481127153, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.13203823352287472, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.28280767234695003, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.20174045447955946, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.33729298835089516, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1667112120846934, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3259291852615986, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.15756751766261828, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.32067005734881104, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.16201038834403217, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.30711349527774556, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.14860706919206243, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.287605443809237, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1667112120846934, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.30913125513655043, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.16192940337079562, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2773561971049196, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1718526210271666, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.29566636692043397, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1716931385864913, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3193195680733763, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.28606398627870955, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3809088476029454, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.00807613785691931, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.41749084544527715, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.5326296670386377, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.3076950010419899, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3660673946004631, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.19454290935168922, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.40563779058474464, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.20365290006260964, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.4327934810550205, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.13565907333537272, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.28348064204085005, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.008095753277702367, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.12475528808004005, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.23623824056754247, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.37420316460821246, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6481907872475802, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.10878661088699644, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4101850467281004, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.14636985946104297, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.42477479000228696, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.13490983794909628, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3721166387799897, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.345393650670689, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.08917122947213559, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3647616198018887, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.20455275179869584, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.47815735761186096, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.24433990852597712, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.20225251182568876, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.24199061099369143, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.43083710197985886, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.35617945587309824, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5928040083540559, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.18016643009908215, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.5627168454831983, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6692849204487608, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.5184565490048982, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6742153914378409, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.33904091445927403, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5149735242342894, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3074762344614454, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5504296088375491, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.489751626844433, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.6564932310015824, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.007811176696490374, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.009755969152501744, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.26351629170506197, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.32365707034585395, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4584149294578286, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.13894362470892055, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.35710461878741834, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.13763666698607552, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.35163868522447556, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.24113982759255023, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.15487634919018395, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.36831488669605916, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.12408616318856693, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3652145198143255, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2280725846401638, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.09007790030767507, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.24033534859070405, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.197162821062955, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.22171463088948726, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.3251763396242258, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4533778048861261, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.25989013073979034, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4315532957872565, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4869755956428243, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.4440750605884706, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.49014891057645404, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.34420876516527255, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.5068918436131059, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.31461500509304885, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4233526729436835, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.14023424042019694, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.24377593803204184, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.18900377082048078, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.004693571154544651, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.23316243238650552, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.26637160423927314, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4646735366228476, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.19585063466021865, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.37259242197674974, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20191019088262566, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3773476047938683, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15487634919018395, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.40723956344919005, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.09895499407509596, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2820930896340708, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20566600172876848, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3332179942904409, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.18945235333331134, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3443950901432381, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.14027395289967118, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.15420519149824552, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.10067881517323463, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.3394719609522645, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.5910744763237977, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6719182394537323, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.18260478645231623, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.4946630566933846, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6169269421105686, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.5795328348246752, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.6571878614059478, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.24263763794008045, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.45834072271970505, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.32018866449570155, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4142777372959173, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2735838424624378, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.43137371459498897, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.007847958698936742, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.008115464234465965, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.17226307014894685, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2929617403109482, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.41749084544527715, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.5512835123193889, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2661644792674617, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.46546633658762687, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.21203547746686083, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.45610528927175875, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.08644237346462266, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.32003978062314414, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2816688975928506, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.47573600128712834, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.11460773731685357, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.363038960346026, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1581734375963556, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.29855796123914957, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.17992187611846544, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.17631896061601307, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.1602999168643203, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.14610129766068167, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.11719542744488858, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.5176576778046864, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.6613069296035906, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.6510651028008023, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.7441675183592714, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.31148557892944495, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3867464805058363, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3688189810109343, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4691915858995521, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.3580995277077084, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.4302234254773672, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.009873841081506156, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.0465791689548439, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.11175354227446688, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3298241713743613, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.39245477087067665, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5302932215753233, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.17171159782066198, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4250539223489113, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1718526210271666, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.355144746174474, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.18597468573870948, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3585545206106179, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.18945235333331134, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.42435548400666784, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.16446110196634803, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.33797636030209444, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.16832254701348195, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.34172735320777375, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.1663768231803161, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2598332226932194, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.2543269102041851, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.45657979346800803, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.34876164625175754, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.49034326628094554, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.23377734254023033, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.46390013598008395, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6066709784156303, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.5563610896532531, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.6234143352599183, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3203505804334101, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.5201747871509939, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.18367196864850696, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.36528750965938445, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.3489571331320156, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.45391662061595967, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2684337672133018, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.1642384866095333, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.4097157364333445, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.4592265081063172, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.29896910170538116, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.41423657620328247, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1524830877429947, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.20357681430297922, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.14691264038600516, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.3211565002110335, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5113942347100009, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.07113990450264403, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.26718576718028936, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1567864814929981, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1556051570841198, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1556051570841198, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09802862511942351, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.18018110949421698, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09429247283039355, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.17793742526979547, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.05928666280553014, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.13867167773951167, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.39615544682237175, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.5208357532544405, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09802862511942351, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.18782383079014037, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1414355019095281, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.3460029262848581, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.08747015602038587, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.09252921910030763, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.17272055181675486, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.150668838416559, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.05963570658750385, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.2115339554327366, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.47475604110292025, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6309823582859546, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2685172542195998, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5385038880406502, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.25284666735526534, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.48906659909069483, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.21208798872596596, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.44139630621320486, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.34535868670642117, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6504104766728446, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.17281509196575948, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.46979670326158635, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.4102495208939548, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6896260480312464, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.07209117403380154, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.24854556744215647, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.07209117403380154, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.24854556744215647, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.13801642938000075, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.05278366236265346, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.13670933737234986, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.495122539653757, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.6951565410196323, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.5067058201778797, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.7186203369024515, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.3537581250657245, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5377035718944764, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.00615279366159919, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.2738643930663906, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.5091945154151882, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.0062763757184508785, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.006004997316698418, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.33636994463223036, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.18559542135951204, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3804842882867387, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.35369375385786006, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.13087682931309413, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.19462952976787054, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.013538497707846785, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3375178721974199, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4840651438641062, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3314824344065458, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.47145091131338446, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.20972571494011877, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.395894071208527, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1484131243041233, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.37025679010586365, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1484131243041233, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.37025679010586365, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.16678872216161894, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.38156158663679846, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.2312892590926174, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4296420129947672, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.15082713742973322, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3965911699770542, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.26279137685269766, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4760220740362435, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.18928475425929295, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4916060435820526, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.21940429389247643, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.4343280866601455, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3300025916068812, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.5052501972629104, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.16772893302667713, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.3631993115371921, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.23271849054299032, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.44780782224814397, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.1824401863423467, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.36709433185688595, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "bleu", "score": 0.3377854698776805, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_from", "metric": "chrf", "score": 0.521201229892482, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.15122189206102096, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.26750110507308866, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10759927692349745, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.21065794536310511, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.07843772989359644, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.1324578891826276, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.08163977068875294, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.16171314933474576, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2876418495512317, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17431417316164047, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2946006716848339, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.12475846123062707, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.27823340731817514, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.21028610725809627, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2077061256651276, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.14134641571854575, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.22948919855739472, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10227637589934795, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2639843034394545, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10322985794794913, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.24491122482530842, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17600429416656618, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.2712560798864272, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.21268444697113978, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3229997133764549, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.1475503033983142, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.22104108935973044, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.24911274612875411, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3603818786794888, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.25558860194930705, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.36153214205343004, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.16590723086720205, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.3048601435624646, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.10085167559661873, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.23831215045289575, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "bleu", "score": 0.17543744527808774, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_from", "metric": "chrf", "score": 0.28201016956553354, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.21685485833927476, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3714219747170047, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12274092982883021, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3385513651938691, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1463197333291977, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.366137273378509, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12656494026948834, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3156355830822428, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.2496001284078824, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4448983035850296, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.15110567441923345, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3452827306773606, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.30327872414714485, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.49804213541579834, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1308672243682429, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.31750364852389135, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.1308672243682429, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.31750364852389135, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.13237645860785527, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3818322535970043, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.19532265607774463, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3705900176275221, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.13937542038981274, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3894719473714519, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.16091123830242154, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3479090205359599, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12017396628208415, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.31451281894570277, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.18154235663145316, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3906877817743504, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.16701570871784516, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.4021286881032558, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.17068857826795375, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.42259904419193595, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.12489558671106761, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.34127082262151476, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.29383139922210444, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "bleu", "score": 0.15799783604363904, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_from", "metric": "chrf", "score": 0.3949243937510492, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.112289032173749, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.17726100052085036, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.31017716089889963, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.14276716121505195, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3191375424862687, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.022303919896869945, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.26765226160005684, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.4201493552127268, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.12503614625842938, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3600940511104839, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.12787395553510186, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.33752742535974617, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13628770358024436, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3557485348784759, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13628770358024436, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3557485348784759, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13181313433495553, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.31758120882708796, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.10575365422675637, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3112197010206788, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.11873119582007514, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2738621723440972, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.31669205297743036, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.2662775444898412, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.33753843688529356, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1463197333291977, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3593717322097392, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.1486872032633242, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.33234354320913057, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.11809858631445573, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.32136192142934833, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.010176705289341573, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "bleu", "score": 0.13628770358024436, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_from", "metric": "chrf", "score": 0.3124983184732695, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3710595252626966, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.21688283061839067, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.41775824162589076, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.18235247300784824, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.40779523977234755, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.013915288440632284, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.1949274977582591, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.43455936271970363, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.27011759273645686, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4427599081001661, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39962545473912425, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.42454130154428354, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.41372838762491687, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.39112369376374106, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.38174551465681344, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.3685731277721772, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.25299682930744943, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4798320133488269, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.22524348812603687, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.446814197726471, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2202248274013358, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.48474965676300186, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.45813938111627356, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.2519921893632723, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.5094822088665985, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.40467880605321677, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.1593344703029041, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "bleu", "score": 0.22494952618128455, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_from", "metric": "chrf", "score": 0.4760660341798742, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.12666372160329223, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2650373529479294, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.12162779391619735, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3228288840559658, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1649662542496744, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3466546857451185, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.01536966738773372, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.15884362032938681, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.39814998955321834, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2808927299109351, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14326513489612383, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4034278533385552, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.11900012437357166, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2764563185977449, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.11900012437357166, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2764563185977449, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.13829446068705525, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.32059338352121075, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.10814410080481558, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.26882333913101714, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.13110409944926496, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2967415176257371, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.24951692246125404, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.5427942390000431, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.18357153089008083, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.42052246538746396, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.16521691795932783, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.4134512022176617, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.12366644075037489, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.37651342775995167, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.14937342175323892, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.3978589591029684, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2808463392632455, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.2962222000049211, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "bleu", "score": 0.1971903602140518, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_from", "metric": "chrf", "score": 0.36269646528997446, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.203264842568494, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.2922087191170089, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.18237599479708327, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3740403511567824, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.2244748716483542, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.007281906895508523, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.36622684113978327, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.5409038673960387, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.26632240818317526, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.467076790922237, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.18294117097472648, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4383387744769579, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.18061023425907288, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4007053923669194, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17504630199215807, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.38391258078488993, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17092467746295725, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4340281226634826, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17730543118229922, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.40481314196782764, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.16027177058640993, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3907258279276635, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3857801012055859, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.3917239471102329, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.22860414459682069, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.47331131010100724, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17200673466668953, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.39948318545775324, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.18214748123680227, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4214655347512288, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.16554857129611938, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.41162096051974856, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.10553225565626573, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.1763116500850642, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "bleu", "score": 0.17730543118229922, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_from", "metric": "chrf", "score": 0.4201842844735916, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.1740044679403827, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.36375152376157177, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.12876689524369925, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3253153379449275, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.13269353024089545, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.28998089836851504, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.01357525601063516, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2592282745024492, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3913113624869553, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.25387990321843446, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4061799423946215, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.20298407172594946, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.427376330935813, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.1903260814647347, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.2078396213395674, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.382987159925022, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.17155797860081173, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.38967832102616645, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.10669759380473058, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3168512125430416, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.36557640203818875, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.0022163120567375884, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.17558199612672082, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.41334979014850587, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.24318848592140954, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.501343318078065, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.2759106084908679, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.4112997822588551, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.11436433361427001, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.31764537430109413, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "bleu", "score": 0.13784906211485343, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_from", "metric": "chrf", "score": 0.3161105981607342, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.322788951728102, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.40263021320001785, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.119159749312327, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.21297942664093145, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.1405026510197826, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.24785258181936404, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.022303919896869945, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.27915769824643066, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3696324209636866, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3882967156327901, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.4287492504761661, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15626231814206226, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2918712789926548, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15113194654882217, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.28343069346633953, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15113194654882217, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.28343069346633953, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15325316503089068, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2756316951639811, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15360664677448232, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.28023683151672674, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2040828288243841, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2778060655126336, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2851797100495641, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.3210853623565359, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.28306950244125495, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15626231814206226, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.28318293039009146, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.15360664677448232, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.2898716122200844, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.14063630555225284, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.24531520458611372, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "bleu", "score": 0.3264287329357334, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_from", "metric": "chrf", "score": 0.41662443172249786, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.16925466459550803, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.35912398848424326, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.2036348471340078, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3472831655579266, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.21547697432588886, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.18039960295364865, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.14645066834461026, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3483479830313014, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.13602652550459576, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3002035243994678, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.21397099133614067, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3568171392601981, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.15515668623277346, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3182263053072105, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.15515668623277346, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3182263053072105, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.14134641571854575, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3078571099929154, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.21666466990625632, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3532993717654341, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.14617001423766676, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.279165484305884, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.18061023425907288, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3684591961152223, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.029026566383552038, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.15658994837053716, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3084004707364603, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.16165057948216605, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.35172210628524053, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.1645494395423276, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3395039485255903, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.1762505702729762, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.2840831394823574, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.012458960343878354, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "bleu", "score": 0.20053583653512705, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_from", "metric": "chrf", "score": 0.3585550644386862, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2327080490816513, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4213315211213489, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.24362353508932386, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.14005830765988142, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.28271314565258726, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.01943377856541192, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.31144493768224313, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4723803506062751, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.24250789663911215, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.44127658727390434, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2298971389591186, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.45764667682340326, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.1531305080006172, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3836419455857873, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.1531305080006172, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3836419455857873, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22183437291807073, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4690517750319636, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2327080490816513, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4435738303024312, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.16744134956159434, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3646163103836821, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.1743771229292808, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.46893502773403367, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.15808694325739014, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.36205822086931505, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.15089318423122547, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4354703980715437, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.3931382365355541, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.5429286385993002, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.2147829756231977, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.4454092411234148, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.16060122347918185, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.3962176890519291, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.007237155276460672, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "bleu", "score": 0.22233922818300378, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_from", "metric": "chrf", "score": 0.46750271079023087, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2568191876426829, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.28135849152758385, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.13585608692428647, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.24602093467402117, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.014749122939855126, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2390985318008474, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.28355113133330917, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2769725060346048, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.21361876575641728, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2033571257639696, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.22585782564798598, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.1190636583579963, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.11020510700910162, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2753348107620908, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.31634304472566677, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2462954618610128, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.25512324153300714, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.23562397727650744, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.2390985318008474, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.006249447069096045, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_from", "metric": "chrf", "score": 0.17131793456589922, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.12832055613623328, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.19433944404681203, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.14482189302397735, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.2913876815877049, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1217802106941195, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.19314598726036322, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.022303919896869945, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.26784884804296605, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.42827938621547884, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.18723860296151318, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3744699636940152, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3238973846683935, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.12848668968362775, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.35101287733214975, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.12848668968362775, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.35101287733214975, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1361658548186748, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3295167855876769, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.12053310055432334, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3171578305540752, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.11735344762898596, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.22119961905555086, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.25753379048739855, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.42531177875262893, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3043567522223842, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.12819825042984195, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.36515328991507745, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.21743769222637532, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.4131100936190792, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.15471428129658016, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.37972085537143463, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1322148042039212, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.3008688616645954, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.11914562165195522, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.36399317085467314, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "bleu", "score": 0.1302352098354987, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_from", "metric": "chrf", "score": 0.326035134708999, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.14410670132605607, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.24025207593480963, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.16306957103469613, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.14219389639501667, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3550945020345845, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.013501937941345124, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.1383930915047986, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.35245472074054107, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.12832055613623328, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.239266757938952, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.37693028676849333, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.15815783405728007, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.29907122078670734, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.15815783405728007, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.29907122078670734, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3791177761741048, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.33706259236262626, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.34848136198939356, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3767372261720185, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.33711667257105227, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3284649068899757, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3397876134677058, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.15626231814206226, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3835008462447854, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.14855426866172083, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.3526199873839556, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.009628007582726738, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "bleu", "score": 0.20247469739337648, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_from", "metric": "chrf", "score": 0.4418847146430419, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.9199349282509897, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.9199349282509897, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.8827916928185874, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.9278293769424701, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.5919743410620021, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.8142101616656354, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.2762822897608569, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.24942094354139677, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.8293181259810137, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.8797044719652845, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.23537164857894743, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.689799263500028, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.6642718379939968, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.7768492311706325, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "bleu", "score": 0.7660237942267061, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_from", "metric": "chrf", "score": 0.8523393041110139, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.27434065146872866, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4551761513917315, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.28112283847231073, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2624404628276128, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2044894275649509, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.28937737330135566, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.50463558154729, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.12212865548711085, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.32830246390851203, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.21688283061839067, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4479129164961325, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.09225671760412947, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.2523418211331404, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.09175084684048486, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.25022921632561346, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.1423256407233325, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3890910518336767, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.2834052290575623, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.44636998325082133, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.16809016325262707, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.3578360181550615, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3420291337705514, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.517580206652821, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.21893304385292742, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.24797984721910182, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4497423075151473, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.31443515194397026, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.47095169791332614, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.25571867215049665, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.4214364635384463, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.09975648968250406, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.31737139925438795, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.15310672854444382, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "bleu", "score": 0.3863552232164501, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_from", "metric": "chrf", "score": 0.5712128723523814, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.11460384138378832, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.32308861733051, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1308613527030366, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3063146286877558, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.15082713742973322, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.32932326410706136, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1327211341271203, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3314509193319989, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.23806227267122468, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.43401560728128324, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.14062598436731893, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.31701958535647573, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2112174444529806, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.37115876147810895, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.17297486233533188, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.17297486233533188, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.15844990886367694, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3420386248472483, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.21243241299173296, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3866454943966844, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.12008699630291321, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.28909490209819155, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.29329619543305546, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3509216685503233, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.1357521816192783, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.2572585481186862, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.2045516326940124, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.3580560102192693, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.22103128459583973, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.23814249159794534, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.11682130307923512, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "bleu", "score": 0.12966020590511304, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_from", "metric": "chrf", "score": 0.27356002971987425, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.22974300992320248, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.35766721538849355, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.12787395553510186, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.21931515993565381, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.12066241764747698, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.27545568870085096, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.019283248858266676, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.1077448900968642, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.24768004113341202, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.10949741420907307, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3143619842598707, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.12030921204016166, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2935108999290831, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.03466486739421709, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.03466486739421709, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.2136628330685448, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.17681988003060095, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3160912867877847, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.11670085450653153, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.26006787116266133, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.31285104538031994, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.4986402374312041, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.10273756991976558, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.31893745331776113, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2130931749764531, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.34386259606696806, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2912425895319303, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.44041590401859537, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.2741063450190292, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.45913091016192176, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.10471800982955518, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.30028124645625864, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.0994331256564067, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.3083809409945523, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "bleu", "score": 0.20416354003164872, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_from", "metric": "chrf", "score": 0.302007087079803, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1812045836887171, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.18649703687001343, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.1441966459257424, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.10163106686838855, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.1449839903475139, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.011839425862120785, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1828304652414782, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.261122481009236, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.19316111794720275, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.20236126962624626, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3258121781111335, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12832055613623328, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.22099011517048978, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12832055613623328, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.22099011517048978, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.12217624912667482, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.22607924847614314, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1242416606498705, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.18436029336540405, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.08568635726825895, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.21591747223249003, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.1809496049496168, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.2213733761113641, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.14455493909089934, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.26045772569635717, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.13351234315884475, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.21097478779973527, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1535686541317235, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.286595453551809, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.1258273118584677, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.23521228502721644, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.1222932912515144, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "bleu", "score": 0.27908865215418427, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_from", "metric": "chrf", "score": 0.3015846610603115, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.14288815197601673, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.14957316612525498, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.15892175003851755, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.12238991307064728, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1802916852147069, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2500534855326251, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.14580030099786817, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.22020305668868392, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.23870544239673078, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.30389718661514126, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.10277044358219119, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.11241969208680343, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.12217624912667482, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2594914718095331, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1226659433055874, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2503423204189662, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.11758806799906993, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.19638036904069978, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1226659433055874, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.21460383218365395, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.19454290935168922, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.2850090374144756, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.2741063450190292, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.3186528530268389, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.23870544239673078, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.304002814359566, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.1722232255922769, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.24223436609765592, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.19504951470199663, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.11955848575576285, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "bleu", "score": 0.24214093597439865, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_from", "metric": "chrf", "score": 0.30667375521853, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.26958290276046354, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3771988116643981, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.27675048474641756, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3780460244391623, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.18915983539487516, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3233732862049797, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.022303919896869945, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.2511187197601112, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4502536324640797, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.33668442350030275, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5178614849361202, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17081061355061614, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3645499017230567, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17016486621490087, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.38158712387268096, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17016486621490087, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.38158712387268096, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.17730543118229922, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3932130355670893, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.16678872216161894, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3637613572806523, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.16165057948216605, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3755941713865309, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3999374157919046, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5786384524608545, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.3194362090066573, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.30611912992377904, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.5089658823760935, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.25666145410765273, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.42824842089739035, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.3492520394471386, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4895757696342183, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.1626739260030573, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4029875964220287, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.01218568017760398, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "bleu", "score": 0.28487594977117575, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_from", "metric": "chrf", "score": 0.4793282150965233, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2758862937563794, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4673996585329364, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.12503614625842938, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.20624064341134082, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14539971733340926, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3142480613342232, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.013501937941345124, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.3007733426065667, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4585623736430774, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.18630405675789963, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.39138520850647673, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3615889761528277, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14745425511282265, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.326627179815379, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.14745425511282265, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.326627179815379, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.1307524497557363, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3361579714658665, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.16237908184412747, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3670808372641936, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.12757247160029234, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.2807962808723839, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.13574363003136736, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3517512873782119, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.28191922425756916, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2577701686990218, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.44408712841584985, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.20889290280122064, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.4127473131540302, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.19568336427344607, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3996176422345778, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.21245704249360323, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.3820763688368091, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.20666579426708878, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "bleu", "score": 0.2472264820166318, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_from", "metric": "chrf", "score": 0.44131209510775493, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.28234422994155567, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40408604199549997, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.3368893372278425, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22475293380632405, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4113282938664548, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.02586907629320447, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22495022212432908, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4140027812147465, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22495022212432908, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.42230996708392093, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.20588815727980112, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.41944461991174653, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22208402896971946, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40708637163037936, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22208402896971946, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.40708637163037936, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.17504630199215807, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.42263957382757394, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.22469734403789665, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.43058846803481615, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.11460384138378832, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.29561644965902306, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.217554942150074, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.4124786355218829, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.203264842568494, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.41138829710711844, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.29668873351523645, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.45439697849389765, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3300025916068812, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.48848603918467354, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.3300025916068812, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.48848603918467354, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.23245687974745427, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.44333733713231366, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.07378730454743347, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "bleu", "score": 0.2147829756231977, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_from", "metric": "chrf", "score": 0.461889639754688, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1781853859048144, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.36865727091511874, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.2961559727627133, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.1087256678530004, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.2806568392288235, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.1117144649534104, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.29563794116222847, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.13836903384315105, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.28266806314793996, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.13588969750586194, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3523239132597748, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.11609617787293049, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3030210543724182, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.11609617787293049, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3030210543724182, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.11595071162902998, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.23613460338414927, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.11092325635116752, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3045281033610173, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.122897988281654, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3280398584422872, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.16318495811623954, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.2996949855880253, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.16397906895258596, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.36106327720037035, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.19000969221027156, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.47485346348682694, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.14214337448390021, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3609159299635901, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.12217624912667482, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.3477174082437146, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.12275983234737853, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.26198613287829026, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.12580941330293896, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.25539472441248895, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "bleu", "score": 0.32512365186675757, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_from", "metric": "chrf", "score": 0.49575683948811416, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.12416350645592025, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.23265120010755289, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.12846497020051437, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.2670865602673704, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.12837839907779722, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.27407435258732404, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.01943377856541192, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.2707832297441565, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3606120884713659, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.21222721003696557, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.2775686235755007, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1315376612843441, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3028123600861066, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1315376612843441, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3119958542179166, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.28157636825815224, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1645494395423276, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3212878804764923, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.20690996611611379, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.36853943211180007, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.2957851779920877, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1340616911790049, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.2770773336013796, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.1380829650365223, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.3721998912104682, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.2602720291074952, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.12666372160329223, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.28503812950544305, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.13836903384315108, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.30881683598641113, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.2181762689207584, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "bleu", "score": 0.16091123830242154, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_from", "metric": "chrf", "score": 0.29683125676353944, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.18772266185346026, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4516796575038181, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.28252374116432993, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3549531183419122, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.11203754340102182, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.24500939878540784, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.028862054978314452, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3147237572518304, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.49783234003172966, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.22987974754633594, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.44132234050227787, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.217554942150074, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4362387654025806, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.18580429349907815, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3794437278624784, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.18864182094196982, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3794437278624784, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1457751611852363, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.3555305489093387, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.1761368775330164, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.39519338190185777, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.13181313433495553, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.391804404659857, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3621795144956003, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5514543720034338, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.21311107970920584, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4388024026143886, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.2567411255293559, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.43316022307538615, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.26845008380756696, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.4949662669458603, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.3829453159673758, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.5336098994428017, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.13600287923663476, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.32363483083794653, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.006356553689956574, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "bleu", "score": 0.14219389639501667, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_from", "metric": "chrf", "score": 0.42294374285621605, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.10531636385748798, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.15775047351971955, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.26128489301072644, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.13693974024600017, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.24848210874138496, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.1967909040251079, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.16079298647562637, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.25931919600838865, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1322148042039212, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.31233141405348647, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.12876689524369925, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3034375834959013, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.21189649845220918, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2551309002082233, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1331440297382392, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.260380807406192, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.12235107682054053, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.23169643452178718, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.21608366110461316, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.22194631082821747, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.2586080894830298, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.19814442729413892, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.3102637353553794, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.33957218715482057, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1331440297382392, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.26536762328710567, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.1547905499593561, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "bleu", "score": 0.1797040059786851, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_from", "metric": "chrf", "score": 0.31684376069016223, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1789898550500511, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3097165910502381, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2126837065505244, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.11378142777276677, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.22340791296245502, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.15292856632736312, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2723711009321726, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3950616413683569, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.2590721086053319, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.35495860162749965, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.18285404868730815, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.30239028036773985, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1736086198203101, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.27430743839572425, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1736086198203101, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.27430743839572425, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.13410639648320277, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.2766307218364423, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.13009868453084908, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.28428711747510377, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1077448900968642, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.20612085276116188, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.15022502107020383, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.32915753814356496, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1315376612843441, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.30125329611269197, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.34661236387446376, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.460219316901126, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1665583359843711, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3065906311539413, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.15866683249809552, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.3074056285119982, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.16969453584247343, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.15533586874332386, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "bleu", "score": 0.1629119279942046, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_from", "metric": "chrf", "score": 0.28005921777118686, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.15742302643532463, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3220278551038813, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.18889796346849766, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.390828018955539, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1484131243041233, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.29204141824583923, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.019510108479333106, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.16165057948216605, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.41967247126395896, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3351318042725036, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5017887940611191, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.23292164090728384, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4807364086898486, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3332385910410069, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3332385910410069, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.12690518984438146, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.34504023491572783, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.15533439104366398, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.36668028585184187, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.10487303092333145, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.34114139472506677, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1792939675839681, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4629429664491923, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.16023828054153882, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4268341897125674, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.16605519952887438, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.4509175930579823, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1453056698669881, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.39967038005662203, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3810271038049442, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5487840152975325, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.1580433751277861, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.3469496558541037, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.2533911497972673, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "bleu", "score": 0.3713354961020269, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_from", "metric": "chrf", "score": 0.5550866336796069, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.14855426866172083, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4089031318363594, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1736086198203101, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3517982963278223, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.34932113360659606, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.19118896363692645, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3809795532418233, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.35069983379310715, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.16027177058640993, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3978173363117612, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.15404632289830114, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3934040018417114, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2467667610422869, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2467667610422869, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.1463197333291977, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3917791418162285, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.18164305788156723, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.42992191257005574, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.10629480219240392, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2893247452861206, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2327080490816513, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4453208003026105, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3391544706988281, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.2577701686990218, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.4782520457453995, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.20868721961570674, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.428749486637124, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.13948420003997705, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3744296785576754, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.2766362616814891, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.12718016030558363, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "bleu", "score": 0.17600429416656618, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_from", "metric": "chrf", "score": 0.3699002945708035, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.346045680932875, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4621083930255766, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.25751650996406256, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4024993164207148, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2235704325446919, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.20771980047219452, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.42566629822564495, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2387386324204149, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15606652450871636, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.38676973597326414, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.08842019030033135, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.27025449589526984, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.08842019030033135, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.27025449589526984, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.15022502107020383, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.35815688949507335, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2012788513843773, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4158992611710376, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.10281312610906089, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.2831556428398908, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.1717286307100586, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.44149458986800383, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.34270506983355076, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.2569630819965695, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4638113964856152, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.3110277298634108, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4544814134892622, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.27645608560303897, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4775117408731701, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.09296917759336987, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.29970256002116996, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.1514798524753532, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "bleu", "score": 0.21085288029061555, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_from", "metric": "chrf", "score": 0.4495966880080192, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.2873180113751827, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3691291664744644, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.21636840076404606, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.19001225225138996, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.15902128868434096, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.27967227996169636, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.26474827115975164, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.13628770358024436, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.30464291275706445, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2685078959784482, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2685078959784482, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.056621705833762526, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.20663551397330182, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.08335112496018125, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.1757222237049662, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.04743571775734884, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.12540743214067215, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.15799783604363904, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3478409813873873, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.017418423019324433, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.1342816454725345, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.2947742083176782, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.19968127388777596, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3882998250788871, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.19861626912448344, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.3882998250788871, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.22685806215113302, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.09083570416152802, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "bleu", "score": 0.08340582868969061, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_from", "metric": "chrf", "score": 0.24375361043612415, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.18582826054135923, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.27931164611946097, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.13628770358024436, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.196045070105177, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.24882723725145164, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.014111660160258993, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.11276958806531856, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2856161524537875, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.12692707541575554, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.309191449874187, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.29331713922012836, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.26291153755861957, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.26376991116778054, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.11825188614600338, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.309191449874187, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.1404678994830558, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2962148768788933, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.22350242251322808, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2812642831742161, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.21676612877798807, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.33382277849238146, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2689798160106529, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.11610083023532239, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.2862219874694651, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.295153584471285, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.05338400788913371, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "bleu", "score": 0.15069228960836628, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_from", "metric": "chrf", "score": 0.3780369016923967, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.1087256678530004, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1812150267056357, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.09624090077172921, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.08196612912062277, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.08546743910655354, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.009628007582726738, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1803546807787764, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.13825905140405212, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.23256631645019393, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.22256474447332572, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.027558878227695063, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.027558878227695063, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.10539140971370214, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.08170791430618002, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.05861911252854408, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.11209478008784199, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.15557700252716788, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.02731253201398055, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1612982609267219, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.15080392997556943, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.027558878227695063, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.1476996786071879, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.020035925770441693, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_from", "metric": "chrf", "score": 0.14949577610607986, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.08206174754800233, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.24600065227133203, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.2894206730562163, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.130697570216376, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3655209094420809, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.28364158842913945, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.28212742472349317, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.013800067168664049, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.27274442393032494, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4767475272675149, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.28669684236421306, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.22839803716503337, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.10704604894593339, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.28394660030720387, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.108043996762779, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.2946349659761032, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.02321338950356412, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.18225955227302953, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.4400405224814026, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.02340652500728732, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.14868720326332424, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.31851758158862814, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.16574624158406068, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.39903127217688206, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.3672664653484505, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.23788431027756934, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.17441676789914212, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "bleu", "score": 0.11047111196276078, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_from", "metric": "chrf", "score": 0.34052178710726805, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6358921902612438, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8041899227402122, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6299285159340671, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7993134129243716, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.710159574003633, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8462481747979111, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5487830136896633, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.77238965036654, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5375319287331519, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7826716936890488, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.48244543610473856, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7294391805717774, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5745954681260859, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7920051188244848, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.473743611024707, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7204787094069257, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.473743611024707, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7212488881410557, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6012475603804444, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7990339788905771, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.582501414351973, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7832709523750881, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5293493442903949, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7338751118862769, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5938611220262585, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8079474861665713, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6407610564169256, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7997703697716119, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6660677740125452, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8293798371335214, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5718247506430171, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7570613392550647, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5718247506430171, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7570613392550647, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5934447341895612, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8057808261092149, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6241924127610678, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8031006153647919, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6372502110149713, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8187019874664503, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.35059076445515835, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.40219803477483124, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.41316127706749806, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4430321339435623, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3993284843242707, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4224738565076288, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2908087026261561, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3411361400094189, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.36861518849172603, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.385899929138448, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3504650671187503, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3985617531166433, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3572514590810421, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.40312319760122833, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.367359470372992, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.397303106677261, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2940872474292116, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.37182095401206455, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2996868226086902, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3355531727847081, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3704616277624811, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4166020708416767, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.19450029639430153, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27662361414224973, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4317270147628918, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4476891051893246, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.31869252626249206, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.36089356265329914, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4199243020508202, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4310330650643179, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.38146085172952343, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.40030269579783606, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.36258675084165565, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3828423818810428, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3146999839790487, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3609768423654951, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2613520653232399, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.292974388325607, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.38876512474558916, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.41342876789412997, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.8780634320789833, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.926946700115022, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.7964573357809173, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8458636471716781, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9452996322890763, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9463396364218181, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.8781548422306138, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9156314785041992, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.8562379115188704, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.914880147320643, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6061745621552239, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7612297430473799, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6537803976048806, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7742226743967544, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9878765474230741, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9958930217841712, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.9577952806172931, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9847675380468571, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.738238064391125, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8637738769684485, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.40673971192998765, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6897190926100627, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3707525915417785, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6481906761834414, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4405434565828979, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6872423435487918, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.34070519401434163, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6376396416993303, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.31345365279001985, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6269464695155232, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.38318568210251663, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6625830408830621, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.35601247064914876, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6528728847159075, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3155065747070078, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5938531598317043, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.31724496872686936, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6080661572259668, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3535276144718208, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6399338911163, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.32909385533018776, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6587606187204432, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.348920853132259, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6505040271951762, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.42021658469726225, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7002995337928327, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4142150747824564, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6886174346652553, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.29793763405666984, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5878658443031616, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2737856702715042, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6091441790112126, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2737856702715042, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6091441790112126, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2831940852570977, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6293179946715834, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2060740184460064, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5566122985381202, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3764145740138264, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.660406350984819, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.703373719677874, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7784050705257474, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.469958733898233, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5843756060033074, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.6034601376302852, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7074074363255227, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5200692650497809, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6586847274336591, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.517670839326365, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6443244311395148, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.668895061203786, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7856645013611931, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5724622291345857, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6818279156433621, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4211686427838433, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5788959327608644, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3472652233717345, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.536323502860556, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5439803529976158, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.657598922173703, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.6910600271263078, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7855543051722911, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3051409552296292, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.522746034067617, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.731132155274915, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.8118306465406135, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.7618275371106299, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.8252860779969783, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5447800851151646, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6845859707632784, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.63457045351243, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.760139991277541, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.6515663614401863, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7685095079945828, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5435307013262817, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.646576761573972, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2747017431249852, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4456826256200505, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4834220366915352, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.678862671476654, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3489926819498492, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5715668842319502, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2786169604662155, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5267252236203236, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.35446322216812387, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5208748527454148, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2679728611808951, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.466691372759197, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.32445558465151153, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.557607437471968, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3842600770501223, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6030559477915464, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2676232320051144, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5440246804235981, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2559102158652863, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5013387365293691, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2588692070329805, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5018097349874775, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2328598163544389, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.46604753989124215, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.32150635033114006, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5479695584127602, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.20024611058462247, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.450999802118824, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.36488083606907545, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5811650865491297, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.31876018479642804, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5884644303994607, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3249989390135794, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5532261012182782, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.31400830186120793, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5436299115609682, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3104399267861846, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5390234949668378, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21732968497953328, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4683342448941504, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.180038135256147, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.42760668286140896, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2702404890575711, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.505948742808373, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3410244689880313, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5816669416914216, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4234343012313773, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6625289905598352, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3885765192359091, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6554470157301392, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38108864298853723, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6485553379227472, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3602811871213193, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6460863746215998, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.385626093679484, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6500036127408896, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3765213224289163, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6469521424555786, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38543162152810245, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6356972128878653, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38543162152810245, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6356972128878653, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.36247466608675993, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6011484151165629, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3037425321349514, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5893368096126496, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.41616378505554413, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6576322811713005, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4326013853051836, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6609703936604562, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.35104428234941937, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6071559884845871, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4079926989572759, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6592699047005666, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.26075652499067425, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5605305670545515, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.30994878928868236, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6006061482856062, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.32013340270991775, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6222205233819726, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.13339786348528015, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.46778689835182324, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.2602768294269028, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5310567541651178, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4324680011853555, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5877600878871951, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4493940083619696, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6230960824462234, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4116575552858724, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5665759692366567, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3533147318401534, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5972951640947346, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4771981137756629, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.631576374875568, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.37929353357736867, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6046831629978785, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.44219732271776674, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6193429426274062, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.22913506273978548, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4939257941082402, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.23006243247829844, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5109587983295097, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.41852674506584964, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6035836275599532, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.47174948050634596, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6205798681912935, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.38750084779193644, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5621267916844479, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4839792901878845, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6380327835059832, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5690535070317115, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.694401643850368, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.433056028408153, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6068335862669254, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.37696437834356655, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5617832488367239, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.41601295722853754, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5905243301789833, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3175167304634487, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5599612274230438, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.1810501938660849, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4154005351684647, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5018386916018573, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6673891538739279, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6947677373756656, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7941300666655116, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6412098671661826, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7665040244283648, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6045639360711837, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7576570567798335, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5438238038060724, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7060850657954441, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6197738787215121, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7658055016335501, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6832136298239752, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7617777911358293, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6638859619095425, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7874224590682172, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5298074527457437, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6947127142026204, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5298074527457437, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6947127142026204, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6543739381048754, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7768522458527362, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.662399792163026, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.773536539587345, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6225849492542269, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7743614551597617, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6699094720554168, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8022876242275274, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6967404588441317, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8042365592031913, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5886489119980793, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7611944709376643, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6561309661336588, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7849652413082676, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6563682116572268, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7849957663929321, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5513991164786572, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7476990274059347, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.24311976929452217, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5332455436874994, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5821415139431849, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7329539842616807, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3861375213265022, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5122109329134508, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.32539921259497445, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5133457276293165, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.375079512706724, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5371301483272257, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.48456463733283883, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5906105668854662, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.40927553310427206, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5662949759228756, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.47662407876184354, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5978297795375753, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4845227999608418, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5968050469845498, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.43767708225471547, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5832672215535696, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.43767708225471547, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5832672215535696, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4494703452336724, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5696298539086213, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.5361224072232371, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6206824468730637, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.40043696159688213, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5499753931711484, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.44981308897808336, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6151723374264357, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.44690678721492927, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6070649356517335, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4295014616287586, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5957510678657648, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.47727404239076743, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6081867525552255, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.45613271253639986, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6079134952024788, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.29321566655721476, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4784943256117785, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.01656048993031311, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.11323797713183678, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4124136266900752, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5714981155807188, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4354194543126476, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6656175329857803, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5941815558294462, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7983203558832153, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4524360012660941, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6715594086896963, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3355428780074198, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6348737822745005, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5203658197535925, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.728651597345323, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.35291113737574475, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6466347966614083, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.47269414327373943, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7451099574206652, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3316233171986411, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6272179443370408, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4139457402861102, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6639608785371084, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4216321717480383, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6897801155729197, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.294827064925964, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6191657516508425, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4377505012720095, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6684596427144653, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.6036019309695121, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7801644741948762, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5022206885761161, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7105763508429477, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.43249073282965117, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6444897357478733, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.415412929081021, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6437233280372863, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4847783843624222, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6873592111602536, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2755378501368094, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6144463222131131, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.27979942810555614, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5926090214839685, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2995846558655927, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.599404823793189, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3983045920261205, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6521777108605036, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.268203877206376, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5791297455379081, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.22766536738739604, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5321260120854782, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.14981855747310632, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5073561650857479, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.37767129707620756, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6263797336995671, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.40263336117444953, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.656129562811693, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4143449478847806, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6736569430464404, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.24638705113655374, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5790960837180688, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.24638705113655374, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5790960837180688, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.20430195455630867, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5336103118914343, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4602159439834861, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.15626437596725912, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4715421308516199, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7046296108422225, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4775743055476471, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7017340115397528, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.38187621052323667, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6423162801762098, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3491792142373769, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6341002242155772, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.34677612240149885, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6340001930650527, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2631288867571726, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5489643670410926, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.001753155680224404, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.19348048287912908, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5498004622015639, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.17329990217896798, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.583781848253705, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3373556859342653, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6738789170291255, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.4059531821242849, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7392702727394752, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.4658089028058827, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7584810978753719, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3654687885151158, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6925292674757693, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3725685850787146, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6944058070280722, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3720001389308944, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7013845085492982, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2553027433060345, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.637042750920823, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2553027433060345, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.637042750920823, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3649036594689345, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6887265942100023, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.361621938060054, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7227161818129695, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.18533803782909966, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5623323442262416, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.4058364743511898, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7590590041728482, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.46087901425957023, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7574945544449315, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.33490167163730483, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6738850345838133, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.45475498440082013, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7890162768101745, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.45475498440082013, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7890162768101745, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.40994675674919734, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7134834638811454, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.001410039481105471, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.33415579274035306, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.676792081658235, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4446730260276365, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.755908468739292, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.43478132178539325, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7018196083546635, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3877278798081724, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6833268596614586, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.37529811264444257, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6378039240510625, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.43482851137981304, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6920474811314331, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.400011517795393, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6786441872043172, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4494597917400064, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7073438158390085, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.28932340357490705, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6127615085528726, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.28932340357490705, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6127615085528726, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.35036401492739216, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6426566938482169, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4754775746253918, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7412539060902723, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.42540540518667613, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7419806831321638, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.511936592363045, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7671481459096147, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.46969023925544096, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7315431192429768, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.46625439194767143, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7058896647604742, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.49975754725037047, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7306601419467481, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3862844443359411, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6747509426896976, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.17314327152587822, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5307830562814513, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.42907605083910527, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6942504376084577, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.28038937103419465, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5038494750471553, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.25718495991757767, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4369258127692308, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3035527425754751, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.47611727660210634, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.003762227238525207, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3457321730564948, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5434124381049174, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.30019255581073173, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.49869889490439867, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3268845394941929, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5177343510524726, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3014338594407141, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.46425589256856287, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.30240075980371306, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4633715711061665, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3293368889413212, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4868090313482157, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3090542869620925, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5103110435016267, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.28680063574151565, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4509415604815221, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.4592260218476326, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.6081527520886763, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3446713174282172, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5204675442759993, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3597572114060291, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5404525494108054, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3276986983391062, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.47017897902052863, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3249152568205164, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.47768812495239976, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.461854840187321, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5927663765598625, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.24830299714202062, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.39688820338442954, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.31950891970955725, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.48966432562692086, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2989825848955476, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5979372541912472, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.21832405319137094, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.538599666863523, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3115768268340918, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5357057702068471, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2586945044297987, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5387430998949699, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.29339572010667503, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5936892246932287, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.28064547347009405, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5180716871987625, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2598777182656361, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5891629072611128, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.16456477665946817, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.41285435919616165, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.16655986548078744, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4124447084704064, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3036094747298954, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5533394965317399, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3720337795006881, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5959145385593907, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1533428945524185, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4257635310750525, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3182748865833727, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6082918458674967, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3516027503553436, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6195701584804578, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.14296936488768364, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.47550381383139706, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.40965066226588226, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6492365059868139, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.40665812654558303, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6336046294846941, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.14016942957305434, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4272307711607646, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1760794779214713, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4575853716562964, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.33403393270409815, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5656795429894189, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2607899218485117, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.48702498962539814, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.19112125497758137, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.39870104995538236, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1905322718463843, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3856189128703021, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.24830922800703137, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4179013560771621, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.14715094360492556, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.41200144567386, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.21926096955147786, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4167523577964257, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.15922876554252086, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.39205452902204047, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.270143509661696, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.47453394890664635, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.270143509661696, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.47453394890664635, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.29752721412676364, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5014416567505952, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2251933631863803, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.48308242360890785, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16082381009791424, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4142991984214184, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.29461544890303853, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5209091490119253, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.13140798376069315, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3808902515851829, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.26065672870526985, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.48902571210477214, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2703464256217121, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4887431068878756, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2564158056447365, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4985422502909961, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2362210050289396, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.44300184014250993, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.09001281287166815, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.29678105643425495, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0709787992575099, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3721953235737691, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16158718602920916, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.529420842984689, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11815153359326112, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4449148298646824, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1643968721046963, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.502337586581055, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0665116325665265, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4270729969076189, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.23668163623735117, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5999794441735549, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10479477169090108, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.48965200604299275, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1061903685456685, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.48402103757719056, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.18211387083835692, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4986662704036846, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.18211387083835692, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.496627095959543, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16675794580737027, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4319174282684955, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.08041822969104957, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.39054133168714267, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10676196248444668, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4217035289368706, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11372855109111697, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5442956478878838, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10409229950151488, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5230723702949467, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.13834666277961913, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5224463124365963, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.12602284615352088, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5260100533464075, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.09821580391129837, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.524129220630266, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.07559167521278282, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.43978735666129, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.001993620414673046, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3966243116248163, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4280674425361325, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6762864074630727, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3476608425783186, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6262956160259413, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.426434068388067, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.692779018863909, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4484733265095632, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7011327081584477, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4284560652173415, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.682978489192362, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.42432815678137736, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6929325034163117, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4840168429540741, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.708011141564384, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.38337199664693017, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6131504489318851, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3479593282299806, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6085432841999066, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4860845405802908, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6654842087025501, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.39598369855377885, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6372978936473155, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.13243406366000607, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5138012833661083, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7611872892611777, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4338915749119648, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.68146231376533, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.40431833568589515, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6726559802484742, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5245557811520258, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.758483386076469, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5245557811520258, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.758483386076469, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.40896014720436774, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6783188537179585, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.05352869081949678, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3819546890461068, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6360111897754611, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.31513262466552094, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6088063321214817, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.328480036965797, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5845846160692275, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.37255875421707185, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5802452418652684, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.31783906024075725, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5668993446336066, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3193473733710768, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.546188037439081, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2764303380184275, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5419234868461389, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.260560100033495, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5367621571346236, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.09806297894460858, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3903932427657001, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0959650718435203, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.38796120798722006, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.18642242278321888, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.46911664367808803, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3560731743608624, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5863868433828183, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.24628449712479664, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5007787042784715, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2926638002566019, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5719277380611922, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2560601537516366, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5528416138114, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.28831927729808415, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.581119580581157, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.11379991855874161, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4351192402449332, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.36838655253702773, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6229761260411643, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.20289080919028094, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5022073516929659, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.0020798668885191347, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.08765181859659299, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4198399937062217, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3357114888560433, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.577627721559994, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.165917178563774, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.47788177649200114, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.1589577308024652, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.505896276887539, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.16477445466487844, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.459819964261446, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3834925243677549, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6550089441848741, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2082930998913907, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5532091847800142, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.34818832435375924, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6021958119247758, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.27581307652167925, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5553865940438732, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3223396024323621, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5912894027026766, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3146657215630817, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5835370042710721, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.35158019441290855, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6120838595405107, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.16133896524621585, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5552482281757406, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.42784086863443627, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6882160381334613, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.38591922147783786, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6582794169866106, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.35070110489424783, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6303302920665712, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.30861758644255877, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6190092441225287, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3576059081620552, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6266553980737001, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.18163638157001039, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5268292196755848, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.12478244272048393, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.36067860302550464, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2869154404670116, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5724031955301535, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2715808911127579, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5912854463960201, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3561131937728394, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6360822051576717, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.32531817821640663, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.60401575980519, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.28671896452833406, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5412439325599205, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3716909306227889, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6400806371173305, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.32148367781910586, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6050096649366548, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3962150993148768, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6615791069918547, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3461149674280951, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6080288192802612, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.326661108144707, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5894586069082428, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.24809748407938403, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5410362169381645, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.20939224238332071, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5362745679788242, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.1910176196331082, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.34484093017132394, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6395426495902622, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3483096250476608, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6318122440778494, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.34806159319735747, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6310588996276091, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1329195573506788, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5202656846184245, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.33103091910045723, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6237034632133035, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.20767811562631466, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5422928733421603, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.0012236906510034264, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3700647909339469, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6502447445733328, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.30006024473641996, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3256826624869121, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.20022216695167708, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.25475796453209737, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.12506045850590283, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.13089074029559336, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.300747771019676, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3173961462660331, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.33286620570997505, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.34215490607059196, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.29527663375827945, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.30142023298576054, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.30843187897727053, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3486791970487533, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.23332061635710627, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2566419801141603, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2405665302731005, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.276111632132572, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.24952367521090352, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2609799307655936, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.21308267744008783, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.26013548835400724, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.17230159795640088, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21902099386210508, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.20712109612877888, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2716500132697994, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.40137962383426623, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.38675685523696335, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3893349932266618, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3929514836681183, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4198465413343155, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4220024962966257, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.44578201596167943, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.44136419881837663, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.24000057851120946, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.26789658199295885, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.11631906556464608, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.25578558071981117, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.27270737715571486, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.20138961649645912, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.31544376598852375, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.18010353259801426, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2514369893270279, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.11110503478177579, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22819017092278873, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.005980861244019139, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.22605108973356855, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2500902724267561, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.24058562078978266, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2719774362951576, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23057388791871672, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.28722063151007776, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.18087334221478837, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.18087334221478837, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2316754903737317, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2711134955494406, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.18922003884382727, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.23842255928924005, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.14597727071242525, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.23275105527196266, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.25726126471723726, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.29380082192915835, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21700184332800349, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24253963535587755, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21641035200842274, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2441782821829483, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21649213316213017, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2412402757213432, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2265279670953065, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.27640631169553315, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1580890560041312, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.20972147530113283, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.12340397529268728, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.20444453862205114, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.19611486182177768, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2607156802280298, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3575554083195387, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6357905858551194, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.38341396472331346, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6437362313865919, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3554972580728409, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6081126361279929, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3772896178241295, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6184118090739791, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.343875968447423, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6203080869559495, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.36616653782818587, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6186956523981838, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3878454500259306, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6551636735823242, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4684056503030179, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6820263032407077, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4684056503030179, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6820263032407077, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.36342165475997645, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6210552995089563, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3600088669321733, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6231275718412072, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.23572077943091702, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5451532106521425, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.38833403743974904, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6469273691949573, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.39079551128996964, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6489080988628403, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.36915900473214464, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6363403499615194, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.24929044937149633, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5801222490607234, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.343875968447423, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6178241856628925, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3567821215601251, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6144568170893193, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.24235204007755543, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.522917324145437, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.25613866339667946, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5426654212984436, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3212586102862301, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6200344079713044, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.29542603524950894, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6045890208480269, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.23349565416397317, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5824998907855937, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2520855787839461, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6062602861997253, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.38414552248057476, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6295439096190666, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2968684306569404, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5965916756005551, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.36350084013796624, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6256665663158201, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2789283308488842, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5934703247441289, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2931172960934451, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5995777718150087, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.20585702977424392, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5580925588942957, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21826859708159266, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5755949064700074, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21980750979637118, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5624240512886104, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24845562787570447, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5720910327241964, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3148545032694575, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6192770324499772, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2970503087292613, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5980643974127514, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.32937445908608803, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6217341259690761, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3296849443412897, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6225198704824016, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.27017327254261264, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5963262712857498, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.0018463810930576072, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21919094140903084, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5995081065956405, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.26045893297751727, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4556002624646449, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.25769536520621106, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4479264653484257, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.30518679384155084, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.49812450266220515, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.20790986473853063, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.43810810831688024, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3840172214263318, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5461608432733371, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.27601292689095075, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.479609409219689, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.31094933095062055, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.49068855707946196, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.14924113955829205, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3993127431049283, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1608791791488148, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4188174293611585, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.32978122911079866, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5164501195528906, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3790340178068295, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5755612586705559, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17526112080278783, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.41835629727825396, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.43168198777904704, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5878046851833884, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.27299273205354724, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.47703707799679956, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.35272604744531355, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5246522557616184, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1776418682110657, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4643539241341349, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3150148909766856, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5091327700523911, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2281330714542381, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.45039469008505395, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.03041070289802544, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3554259247981793, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5460727299785414, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.33202003790347423, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6008057921287521, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.5169325988486032, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.7139612818852349, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4906167177513232, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.674851813552015, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.44703919955084814, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6655582120379708, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.44929080614862915, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6890808548811542, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3609839853716293, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6437289665225415, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3833596037687312, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6303767331020778, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2787847531255836, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5553047982045038, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.27255394270901734, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.560183488542227, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4114155281543391, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6302831368434185, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4935048462514883, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6943423484942555, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1515895761088375, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.41903630508369216, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4620212793693587, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6929628328392371, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4134846607579587, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6553595923197755, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.42152926358064985, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6613648437887835, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.38603411668768844, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6493990798045837, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.38597038935683725, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6451087674684899, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3627829136084678, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5991830267537791, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.0014492753623188406, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3088416770749959, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.592900878888669, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.48468513699279653, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.627759796330558, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.30044261567697145, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5072959120235889, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3508149210340218, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5412873655506261, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5060360517265556, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6405988583997455, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.6276032281768119, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7074650729422788, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5486141288222729, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6319028690820276, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5350553356274835, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6061404961531679, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3896845293886086, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5335919786909975, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.33162808255530973, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4841083339891595, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3812595798653677, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5540173999726016, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.281835618300566, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4873620919042211, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.30276219275305616, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4761465803265626, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5487552982567756, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6792265965211294, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5508944416251419, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6588533619086353, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4935985544773577, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5839815051859267, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.19590685591514004, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5086260671383968, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5746911772458507, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6684658929287185, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3281583483538118, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.426617457491999, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15854102708982298, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.29816951752658855, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5077054904758644, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6413587197895713, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.10167233309625472, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3890033983715864, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3452100271202966, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3365774376014292, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11212490144847859, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.35810167137638094, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1530769479628908, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.38999571084193796, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.14059082344844442, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.36810674844102004, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.16111837221606704, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3897870969473364, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.06638808017417316, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.35588296621314414, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.06357046508728754, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.35389427159747067, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.09899176577073174, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3565436122576164, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19038191039507293, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.44678045008872613, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.10551537698703499, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.35068439530150025, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1965846862574398, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.432874358322642, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.12843357570124533, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.41736340554194123, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1448369993567943, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.39060651030049987, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2881123154846582, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.08452508050159857, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.34365275227384534, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.14889383875898862, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3891856763439179, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.0007098239636570131, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.07859507887728001, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.34793858380348625, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3118864893794733, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6025015600895789, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.4136053909671976, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6322647535881054, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.32738231617619146, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5178441994716841, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.33239407888861344, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5517145772037151, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.38521342747439724, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6429066044491251, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.29077749224583394, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5054867926717619, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.29945813065831656, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5652964318283186, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2827954145826843, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49852160493934883, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2854020994711665, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5032170837254859, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.28872738709929546, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5546188227982165, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3128156975833063, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5919269831732986, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.26240469087814977, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5428010725896136, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.37284549147595164, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6659031225862503, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3320217594322534, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6192339182363553, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3024784802029001, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6011904529037848, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.14197937102005218, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5124141579106466, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.31655432248594445, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6093384140863397, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.15346840690325161, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4338689860644609, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.001621271076523995, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.272708665260741, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5856254575566864, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.26361261152036314, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5725817956180734, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.1678792928110798, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5011442124633559, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.02662451504569158, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.10736906463248816, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.24213116854522995, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4880061744544797, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.34632821240024325, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5555330144056625, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.30129541227386425, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5580271496335837, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.2170322997863664, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5313522319806132, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19108485535364833, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.44330638580686244, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.2055691815843588, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.44032837442459305, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11564238061024554, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3946570545606821, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.12964303350477555, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.30757806042360225, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.045073226570505734, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3072344833719616, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.47030940521087083, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.6313130600162312, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.426869842681755, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.6231228373188124, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.09626171192133098, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4030384334867132, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3040281643947945, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5570113610277189, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.30553566538204696, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5414414179536475, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.06634490094756204, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3933989156814178, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.061647053376497875, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.1554907346188576, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4319476007109481, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.31924314606108933, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5643587039540041, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.46465436703612695, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6187472056628097, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3106871546015398, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5481440119652243, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3812607926267945, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5800153448910886, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.4214243411279288, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6022332200292522, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.40881835715890286, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6176764063902023, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.40476128586074045, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5819090999793647, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.31433899798154447, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5302700213057665, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2500141193775793, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4962715087072226, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3219984326515652, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5410548940338055, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.35814583416540713, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.565376261866713, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.20366453872893497, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.5772621756887225, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.69776600214117, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.4597577036346123, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6387649358449012, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2906050917654709, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5466988553506439, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2813982099058976, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5330166410689565, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2813982099058976, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5330166410689565, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3987369340280224, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5966252340653917, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14629782696806198, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.37024417034105334, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32251358317473644, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5152627703184472, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.14222805709331154, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4996646755261327, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.19867232982300087, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4721193400035613, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1786760469371898, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.44033730462672854, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11069519754858706, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.41088429499755413, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18861865099009703, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5044545567138358, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1643795274638477, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5226815528917953, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.23765992259974003, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.555280304898008, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.07475227349054883, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3917102662716776, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.07591053074393217, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3680248117024705, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.004206414136417992, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.11624166283801136, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.07951687821150766, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.1785438178241626, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.23167461084261498, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5805102619993613, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.22920293798023986, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5302965636981034, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1782141139149533, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5052627255314486, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.24423980006414553, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5580259395074147, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.19726119412992152, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.527856705300845, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3544044522309282, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.001968503937007874, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.19386382603148064, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5282523988633897, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.30065550001026614, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5078021900511434, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2861877593848395, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.497612333201281, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.27099887927850697, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.49735991145649855, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2269082917867594, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.41247660565256244, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3564226671132021, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5759796085098173, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3209133858060272, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5100662436119883, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3540078976511945, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5545213530835353, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2118766389121268, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.43651139895807956, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1995171046317962, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4153129741061397, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.11756843853580158, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.13583465343472367, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1603296850044792, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.37078357002906864, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.594665372689691, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3656717313145023, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5646486568757934, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.34558148449270437, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5585506842803649, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.31930026329775296, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5301066308219036, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.11123595447088756, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3100651531983498, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.06183503355439259, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.23339083303276537, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.45781415663727687, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.3880515884750121, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6587916715823183, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5142726846179982, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7344716263345912, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6066498620510337, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7812137754227463, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4342750764549485, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7115011221714777, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.38939692979759266, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6629460107202892, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.305730257543728, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6305034408922697, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.28822910320599077, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6087031937056202, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4235901905046571, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6897643314228233, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4235901905046571, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6897643314228233, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5011893046413795, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7089203664957927, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5443441840177868, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7408492383397802, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4096284280333042, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6241258962315377, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.48186321118136805, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7050536782800418, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.3231928392518462, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6353582763408947, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.3406014428030703, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6514548680180557, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4492327786840591, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6917786880624969, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4492327786840591, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6917786880624969, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4682583023691399, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7090532819754138, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5105553787243322, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.44571331402556874, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.67235059873138, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4487746167679644, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4476730201191672, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2836623400057614, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.29147337237183046, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2775905064108025, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3165767280260291, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.28912432952036243, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.31119603942667584, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.36793172580653655, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.36238203264481056, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3652139786200916, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3824205406345779, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4094748015187699, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4288513205758089, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3613816886544421, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3747448802797138, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3613816886544421, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3747448802797138, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.35430370029300495, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3864890531682498, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.23877027184328983, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.30469172536496925, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.20137543786547824, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27449035341376643, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.5702271610495845, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5772088119985683, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4054283523843365, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.41608551048864156, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.37405604379521823, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.409758558051675, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3835611536417376, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.41360439536029553, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4416093606258131, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.45147509940396857, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3513670909441729, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3757759666240857, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.19333361726926898, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.28056620588920506, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3541652369790141, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.38739546241623046, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2113054108348111, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.44238229987470284, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.26207903587847736, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.50073123223194, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.16098073041469485, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.39710375075643284, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.11465623153412556, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4497512968651573, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.20350864435725843, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.42265642784768853, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.1866741141650009, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.46590330015791137, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.16950698451288215, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.48668984177868246, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.14357645942230385, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.42910391585605345, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.07762075642455304, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3650474475262904, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23516650478671175, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4885052730214997, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2561279176480246, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5381058353070057, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.1343270650805756, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3620549501198994, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.30632520148437686, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5904333377596244, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2379983204095325, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.557901480722127, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23477037244978113, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5165217514090542, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2711981710401392, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5555651822168547, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.27882680411780003, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.573831995268334, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.16424304323370437, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.47015962613702633, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.168777027092081, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4368481165562445, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.22415590998535484, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.49981791926190994, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4556160153884204, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6661994452325181, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3216756020053242, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6141241026166391, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.43369048469848437, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6586872889176818, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4098419224543478, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6358736384460296, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3916220735299235, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6550784354069854, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4310064928034671, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6681893438144855, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4527112325797497, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6708989870027865, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4656080680369174, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6768276245760189, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4656080680369174, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6768276245760189, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.403282335120862, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6319223068216205, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.43198701643600734, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6357518563774851, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4008289023648176, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.619515936983655, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.47486558569605275, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6916379662719394, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4194404958713696, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6621110611553065, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.44234482870142466, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6617260327319175, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.465541200947692, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6735988737803571, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4650859079784916, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6778737063187279, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5018812162175532, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6982877049391611, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.37462930793644134, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6297969107438809, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.45236333724230443, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6557435747309683, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.37570809340937233, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6339141734561076, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.559332422592187, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.733291190094771, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.48457382450313924, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7144409873446065, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4881942815467274, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6662053431593723, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4577386766301953, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6531477300791018, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5216581079910853, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.71892039370478, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3977038258772401, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6202897864314184, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5071615322885569, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6902107811249504, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5071615322885569, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6902107811249504, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5024073848733999, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6805608953669952, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5105445285326566, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7006788698374967, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4375567656377118, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6314357170099009, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5531306492249056, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7508908077947477, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.48342250090939853, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6678984764077726, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4198435178617755, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6615330486958915, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4423392581565186, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.663370348519268, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4857904515144913, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6855885711252954, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4650185344284313, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6620634442558946, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.42298863290550076, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6260112466527037, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.422714343026006, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6266965858252854, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3446592076818278, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5819912583909785, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.23270938096152352, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4490269267329941, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.11634468327243708, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1766119944524977, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3986479587107995, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.36572840798667283, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5794132414395217, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2729012183957552, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4275664216118961, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3167585643537871, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5076869840147092, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1485909701386744, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.37920460252872057, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.14913158540833668, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3661331120085608, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3292454551002283, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2817018331209101, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5332946673019744, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.10377361777079974, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3387746188862388, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.09073980329024364, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.4022599112382079, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6108631094489827, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.25751023494151143, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4697665795408892, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3212983212315964, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5599573621112933, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.40185909552300847, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6025771204693394, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.08981148917655501, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.2560040742784669, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.09236883467211593, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3472719365557752, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.529527758323629, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6540432510655854, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.49704232910799745, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6453248294274054, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.49704232910799745, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6453248294274054, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5494410974163585, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6853937472090788, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.464523041040441, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6240758263844317, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5201554059039623, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6912283534522488, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.44114781827798216, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6241365710582877, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5525047617046378, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6971891434573309, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5525047617046378, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6971891434573309, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4286794450695727, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6365023289177463, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.47406277913160133, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6744300843116897, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.35313312546871106, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5770478822626409, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.48149733895714797, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6355577992154319, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5280706683356512, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7101124584086957, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4744991305294048, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6720481841701565, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4946489712934811, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6635756951391838, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4946489712934811, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6635756951391838, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.499920808370058, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6982198148797377, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.32345422777393923, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5652905380017423, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.473424955479643, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6791725069180572, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3479698393875884, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5760833125751785, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.24373253714463095, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.49482039214573803, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.312050635062637, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5390444512132623, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.24229889794871173, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4853505495636382, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.27597105261790716, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5468536896755547, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.25483341226864464, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4565768361133673, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3542266508664836, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5643413028542406, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0798787470647272, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3626462425183916, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.11365874698773852, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.35898391291374204, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.18282456123768265, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.47540661243586124, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3634148417932591, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.606148757613633, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.19912607659637732, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.40793214264643957, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3721154325198309, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6214976185877734, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2998257682809658, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5433673039371607, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2921982022041547, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5264166199754001, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3142825719425009, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.584353897647861, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3721154325198309, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6246670078758891, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.06077234009981252, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3407473281004383, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.17473028966988555, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.400425072418037, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2988697040013311, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5442522660489195, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.500703635659656, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6501904887399698, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4876463179677598, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6113405963585182, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5199813503697857, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6584629522606407, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.47431965025538014, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6291489876001155, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4767709962267032, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6259826462063701, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3995439803178399, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6021193793256325, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5428215191518801, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6623001913762342, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5428215191518801, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6623001913762342, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.40656183899584336, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5890799945028116, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5703676203923652, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6860261633054247, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.41482837856520677, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6168104640783212, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.49952715015218047, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6422528647342378, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5142542955490234, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6424880376323772, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.528547004876945, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6459593469343872, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.45002572171222577, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.620458099259989, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5050700246992413, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6475387594613298, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3614492694100171, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5766912416178624, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.27875207406965286, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5095968928696253, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5576102993622991, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6640761861237344, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.43330223254789785, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5564499529933307, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1466607445607986, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.36552963821230766, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.20527494029659898, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.43586475049009993, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3047577636054668, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.48318512703629857, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2580795409309559, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.43914026663016836, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.16510240061590087, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.37927849234648453, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2993081268625724, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.47777429598730525, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.08164832509153802, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3152419985155113, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.07930561604985777, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3127076147872426, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12340057804403023, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3331532512757645, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2533658570671817, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4526653760708659, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.08576088673755342, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.32805247144500205, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.469516870711376, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6115882471919187, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4488093387952295, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5788970821297579, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3196191720459511, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4758634857690128, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3095674062940522, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.49847201920427264, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1670991646237069, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4262476443999306, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.07802167298296538, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.31681677382456264, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.08748671768279999, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.01250047619586174, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.12383271014582256, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.41807822202441103, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.577545891208518, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3475258894340562, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5729813197277963, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4610791064938662, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5982792041883009, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4642320266834861, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6555816107178817, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.0007348618459729571, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.38823222788076894, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5684042820738361, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.35312894221988256, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5483853808672988, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.45147878499907884, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5848017728755368, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5084875082100132, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6086126309449248, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5148124488217735, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6443063241500353, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3731480983940342, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5483607294813455, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.19545643680451924, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.45542992428164836, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.6009332869110189, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7201156007131091, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.42201842197924766, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5864023472716742, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.6427952895393818, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7611062226622591, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5908781325191875, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7135251491959551, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4051294289366985, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6289236919386905, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4267442071795165, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5873661332463408, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3202249300680136, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5240877863757325, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3021474642420404, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.49488718577709084, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.20238796310390209, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5665467522687606, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4612469192468151, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.689540484203802, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4688149931788708, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6935921004770637, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.31907001507985117, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6396787125445289, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.42575254909588905, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6704469753084539, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2589941364530944, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5932208556546101, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3473313422920779, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6495220842154038, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.44311394435253, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6857046279564323, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.44046108667071515, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.685227653600115, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.15605718228191343, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.48559902973042135, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1862321333812371, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5434259794186684, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.12928195437567142, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4539578151160054, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4537382610431785, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6984640606230582, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5813201988276469, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7732878388618204, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.48361343491637904, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7036055457806847, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.38248883198762607, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6879676788132258, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4685867885254208, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7063293525177913, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.21611447762886524, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5783999378427704, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.13828520206051664, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1943642066325126, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5437845506934148, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.45718638941364104, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6765316874457515, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2842437601270078, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.616554183160495, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2790392444035496, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.61628786229813, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1969296745448077, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5972281991369082, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3108511413762713, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6249458527250515, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.33159620794115396, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6420436747364323, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3319181496626261, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6296213700542458, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3644356127641462, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6333838791879324, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3644356127641462, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6333838791879324, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3239007562192641, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.632048088218684, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.36455043938934395, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6460222600356587, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2330073650181948, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5651770800376458, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3728937115586142, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6577808113928253, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3859055776419563, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6651384368454005, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3668099116926436, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6472192230833502, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2912353795089198, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6107975281071784, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2912353795089198, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6107975281071784, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.21326712180309276, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.563678179720206, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2493518765085485, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5378176060849199, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3199241796546606, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6151079711025308, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6260866791475674, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7122695616091047, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3856140451435003, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5942230347389459, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.47809357926196877, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6515239202890919, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.45010740912530395, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6258219368613708, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4729242406289264, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6516452341616961, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4876819889238188, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6502930111654278, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5145500336945869, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6710712793486331, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.44650626058382614, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6393035001487706, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.44650626058382614, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6393035001487706, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6152720493266995, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7135410085152943, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5631686113493045, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7184482394204479, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4545770466847879, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.618156071536431, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.60059205595428, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7065044125404809, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5848425044978098, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6948793399158286, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6505785903453039, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7498687328904513, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5099789058566842, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6591589669208932, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5274166051698492, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6781556869000741, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.32481728488530576, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5086455217662933, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5609895346624986, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.681370247009325, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.025127088788317715, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.21031980892802613, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.14721260533033206, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2721389124032325, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.31315822356102974, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.37596627611906025, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.16777402882140335, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2760884586584135, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2504706648057762, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3683837339255408, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2500271340971054, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3785374220544885, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.29427156769985635, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.38674923884011136, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.292199920758876, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4387549485056524, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.29776813591532686, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.43498932645957955, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2923799210557074, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.37275082068184157, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.12967217202146777, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2760408327025785, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.18371750884517982, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.25880501169420894, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3995850754493543, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5087563569873156, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.06706674495634783, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2609736645923168, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.28256258503905557, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4403352184603733, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.08149835562288019, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.22869808598813696, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.37305234678529364, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5149547593330109, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.4188415744726475, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4486815117132592, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.12394169238067233, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.19833625372206998, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.17671397515361123, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2956531697676844, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.23333094197299464, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.49932033002402926, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.11159818222678333, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4729286927154353, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.07043017228845555, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4191306757394529, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.17011874208765, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.42603202246343985, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.11589839803393029, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4642618457479359, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.392011058805531, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4224062856802975, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0560612491216656, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.29667884967175284, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.13616753594738606, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.05059530408535041, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3965392443405426, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.12656665377079704, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4038727423970976, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.07695254102714547, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3675548828619689, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.22438996279857726, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.510666007287132, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.204118864406014, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5209095484632319, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.17273369377646117, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4962992066513333, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.40336122739639907, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3514306358044619, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.11253965279954393, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3312806076267322, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4060492501139825, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5683580956250115, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.24406315755131383, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4895502947549771, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.18506675761729544, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.33180904892662333, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.10878690932666137, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2847045760566851, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.33882318194431066, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5047311452330864, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.252348200648097, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.44101744642019985, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3095017641836787, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5048955319030237, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11733446372903365, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3700951716975203, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.06040259454298557, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.18644218459633172, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1787841699697072, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4302346068514662, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3896656593774665, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5661203320687994, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.14467877387944345, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.41250682657762056, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.38202772639517846, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5663085006069273, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3422256853930671, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.572244640299745, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.42152658422854977, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.6140840595084299, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.18829060751796134, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4750608803591822, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.34709531432802904, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.512413746971933, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.08136547129100896, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.36756815874876, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.008152391697655444, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.12885984770237888, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.08482964569751385, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.37059552449706873, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.07640690432316208, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4641021856152639, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16305626357596484, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4931017709619054, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.100607017773566, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4914538834431842, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.12123898135089006, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.49565291998466804, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1989354390390064, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5787262395513628, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2282403145147831, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5807113513194252, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3534880761230573, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.631198012145244, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1846217208650883, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5452524689405125, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1846217208650883, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5452524689405125, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.06829403401932822, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1478699652896728, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.44530449583576903, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.31494693194199885, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.13377365982495612, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5270242775913284, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.24729575836552034, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5673652711315395, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10737595646578652, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4590576572286579, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.22617570410381801, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.568153735908772, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.29201611245206655, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.586127589003777, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16100867171758365, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.525256386579363, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3548850735136589, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.17868791441337914, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.49233505722359083, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4264281995893693, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5686715593689737, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3755133068349505, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5350958966397039, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3604013045286538, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5240948375874741, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.42380027373907764, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5825787222593419, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.35896346088508435, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5234247995922829, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4597295132616795, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5915321092794668, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.1806974226541495, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.34826902612300276, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5236428393720809, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.34826902612300276, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5236428393720809, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3896357749382976, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5711687057303002, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.39901184766876213, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5638068824363435, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.08308865150118551, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4154783517972104, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5523079443545633, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4560256553756281, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5819378877070078, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.36146694802217977, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5217871951951657, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.40621309956458085, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5705677721515976, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.37857007405534787, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5432976559190418, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.41974022583187615, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5789182838893838, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.16851048608687724, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.39269226415104036, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.35193239373450247, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5556135973396488, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.48773160239847224, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6806798635651312, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.30528565543580843, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5318320483880432, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.42564879277646966, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5834916199322795, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2816107594296114, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.47708260904446365, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2595156374159681, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5213735061343449, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2529362972744106, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.47633013346678205, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23876161112129105, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5060111681210002, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.10996317447417582, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4562725637074783, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.06283136506124469, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.35716545980725684, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23207681151022577, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5542533872428013, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3681328025423664, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.558946231881744, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1610181647616454, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.44401980465688484, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.4488857379742467, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6217229021975876, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.37214272882689936, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5776707488991393, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3685432686484428, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6081703722373271, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.372741651699079, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5562538159679055, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.5270835405692063, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6545175152961233, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1463099542325129, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.48200454621829203, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.013528602079016893, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.18394986790099302, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.267738825901029, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.558747920793312, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.09056338921321325, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.35831291876413535, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5383434353225599, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.21309892072457706, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4807665621271328, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2751568390064031, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5062735871956761, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13878568111175027, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.31242003815205044, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5563618145874679, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.33552713250034905, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5622995574132048, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.1350251422473041, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13187231723607926, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2453793854893252, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.49293512322505023, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3340915684104956, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5881616164627295, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2231805576223107, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.48399526463420434, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13831234995224262, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.37353627859030286, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6199557289504044, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13044102074288644, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.43717039423668463, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.664436310127455, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.5116998504087426, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6764649727822265, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.14133527729676643, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4869689368209618, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.14885037234207188, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3683017467934542, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13910441643722132, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.36925904697255574, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7332676622154629, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.22701436815032078, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6596565788920288, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.21750412168041985, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6503148632624418, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1255606329059252, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5394589084862519, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3365506763118682, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7035699246803807, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.19743714411828858, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6726680111377844, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.29353984288388507, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.695138133719427, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1859329553189182, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6312651889606834, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.19698875496087567, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6426381621698721, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.12502549517250966, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5134519176715009, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.13078499079113903, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5671925386952724, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.16114368592099126, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.31381150232540356, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6729359211590943, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2762254293612262, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6512210577651574, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2485715475529631, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6619189737616092, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2443332858855278, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5746305891359669, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.28631922426989914, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6564670370777995, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.09645378139499047, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5692397577624126, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.46092365794867524, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2532325989817117, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6340502380249944, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.18842393723950338, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.242345930892648, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.14033475286594138, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2185459072776493, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.15440513664352318, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.20094346456661977, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.19947388010084352, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20584516821270868, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1643888714136299, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1552450511464302, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.16896348843364614, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18418484596876458, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.21460501386434508, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.24916141637142014, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.11335626239247124, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1938403364799882, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.12987138545874835, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18852965533555474, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.29074805324424113, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3256819925596258, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2941832965408921, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.29022301417720925, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21156470995540266, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3764522333698161, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3811591130797367, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.28023341443117344, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.305113560344023, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.19368866426178633, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.25076687061996783, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.11917829382682127, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.16122680340356227, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.09158971449230888, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1604651736249577, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21475571940851748, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.23332152661609917, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.19089930432372385, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.25962807098290386, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2262772028110626, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.28390860213680813, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2533922732210082, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2943322308733634, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.20407692159771756, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2928742362146829, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23258136002668917, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2968944499287726, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21966878190344116, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.28531911189599546, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2385000210355777, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3189153081904016, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23325505861671608, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.32216634867002286, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.22433948264456524, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.282183022851947, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.156393512642663, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24731090719513005, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.12860612501976387, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22143675653609388, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2221235626911707, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2906383281974251, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.08220959497313386, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.18242471007512046, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2078787665206437, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2756656981575715, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2206771360207329, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2933989965217572, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2286976241275377, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.29912179287036944, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2509281473780815, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3278628963365103, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.17151210435282105, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21075293387410687, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2893821949552371, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.24780611716850762, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.47134154774689047, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.22071227044983457, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.45625358803874827, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18572499842104812, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.44634283332460656, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.16045962097781283, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.39926109862673814, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21696202869083803, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.450726878878052, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21671712256611847, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4510971285634406, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19068201647342703, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.47264292072872943, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18402221306466232, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.46311339911247473, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18402221306466232, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.46311339911247473, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1832966984886601, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4594348688263129, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21671712256611847, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4673219674304703, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.12256777245297515, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.38884595455998683, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21696202869083803, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4542389365828182, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21816681623776085, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.46537342956568817, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.22295499304150054, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.47766237893678676, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.22295499304150054, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.48230017737333225, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21816681623776085, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.468844756103637, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19068201647342703, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4764825215004141, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.052213612047483024, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.3400818524793406, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.17037567751599617, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.44610427748565656, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.37051721129462284, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6498104569938186, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2580007063666063, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5822544210906975, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1726118391167977, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5023852140556049, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2359703193429221, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5552647086717654, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2629904892589347, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6085636416475416, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1862014063118161, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.560745680895326, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3786316249953693, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6635410443202763, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21961147134282902, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5737658144410308, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21415796439643678, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5842832527331845, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.19729180187303783, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5692505097947306, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.20558970366346235, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5814353567611998, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.14240979097995507, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4730976331957879, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1949122052514416, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.562469018867901, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.25886046887579395, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6034516113607118, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.34133265816725017, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6366815217770301, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3800346950970518, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6452882639363281, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3783339819364715, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6593521342223361, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.26886359928085424, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5762551633274934, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0698131466480269, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4083625991769138, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2174421310712539, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5984930470698431, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.10361823626504964, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4310581309821413, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2230178035253426, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5101738085806462, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2022608472298022, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.48309607214155004, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2937928216821887, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5533712218959137, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.434861015152756, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.6160254003525064, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.4275132190811836, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.6183948028416776, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3384715911287291, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5853748388768727, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.27076744469211, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.49404709300383315, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.27076744469211, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.49404709300383315, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2270708174569185, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.48624546816788206, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.21286864758348062, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5101291767382903, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.21287094606484727, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.509766683670224, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.19889636825142532, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4442470563066048, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.30945224546521716, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5630983761409516, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.23181745459940442, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4951093505397665, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.24038870654195743, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.49916550876761034, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.38303366784174964, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5620304430819654, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.21123963087126463, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5078608171293139, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.21286864758348062, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5101291767382903, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.32524223671805436, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5722293206942193, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.36794933674561564, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5158310722885024, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.11504003871888992, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.34098902843025203, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14417769394396596, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.35807445053364595, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.08176715535784833, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3376841807558391, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2774818103451689, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.44113079826164325, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.21111088301177083, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.40279886474527266, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.09986058288520257, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.36871570224848776, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.16631693106339326, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.39159831614417295, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.06964145711431875, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32491647022155745, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.07276433052402366, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32116136596381284, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.23308174848162824, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.22218552068256323, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4450748679632032, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2702057908347154, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4678766241841472, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.17699163364196366, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.41857874045442445, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.09553437121825695, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3595876505396123, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3118241997140786, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.12450545657451231, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.34797690177486457, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.045901997129390526, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1702227105083055, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.39357471857893617, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.40551649928110445, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5930648846584049, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.26393609309752497, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.537555561645112, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3303117725880122, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.560168275325771, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.17503312584389935, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43133110833149213, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.43900485344233137, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6549871625186566, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37906205367803575, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5725673261037826, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.36601964108639373, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5845337385286451, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.36455710643820927, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.514430107863874, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.36455710643820927, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.514430107863874, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.1812076974459594, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4487884876740554, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.1883530449151216, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43047232893800663, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.23572045080741244, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.46564299111426677, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.46092486073366884, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6626661413371057, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4174698823555261, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.650238295834434, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5387442820481836, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6904491113602272, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4282802115951284, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6473023220986025, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4526263247089748, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6652966172067265, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0703435502132088, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3516259272346158, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.06672319655621395, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2955579944734376, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.23168344117683473, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5068903585027874, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.17929000882953408, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4496535426738611, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.16236014331815277, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.48989515178016146, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.15735842874768727, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.46857817235250293, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.18862094754879255, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.45176760894555584, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.09202515283226734, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4638593627310442, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1330961608942028, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.45025136594118575, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.08722778492512923, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3364641574903517, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1476568104717575, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3849224616617969, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3775112600948674, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11864063947615534, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4500029014001494, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.18688320391897995, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5004399871729917, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.051728432773177326, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3142433454993249, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.24721511426925932, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5442406939070432, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.271853263303256, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5585854392009959, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2959455734694776, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5713837604330028, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.21688053959403902, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5062525360225847, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2073783805337231, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4984632492146573, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.32520872522373195, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2861595664904719, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.12357944977207799, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4078633867106628, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12507294238386796, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4138228238855707, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.09662080155533485, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4004063786929589, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12582532774374633, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.43332988875216105, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.10101514465264909, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.34334971796824104, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.34499321757027035, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.05192269447013607, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.31860591509332514, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.07838231858034365, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3561023397717499, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.035585322625341406, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2801274742887161, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.04543034413119372, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3455689507412121, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0048954756112974925, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.10879120802014058, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.10369660120128882, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.332527913188454, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.05487814270156122, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2827591580294265, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1839647698105875, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4671696314237755, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.18565720303394231, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4755242091997159, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16231907283663688, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.461275557483938, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.15101262144193833, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.43087539057782914, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16933060149572027, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.44273639204747295, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3134098737361091, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.06799675342315524, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.09997603846232973, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.34271284178793127, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.31930298094188314, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.18843423878971213, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.406619208342576, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19081286150787086, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.39113510970460724, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.20120733641434646, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4077641022795532, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.08237593849286892, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.39211133589483876, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.34044840921931474, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.30952716928360685, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.050197821982229, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.37264360189446266, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.28971150857646244, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.13891712410260026, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.042989735393950027, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.30351385376698004, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.1200764997254734, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.584077802245465, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.718852356264379, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.525804146413243, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.7156057074240233, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.08851034303538526, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.35420441276966086, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.14180177701637703, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.44423269039394, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3561981735709292, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5123206368687799, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.06855125388880344, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.319498334710369, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.028396850905583346, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.22336951391800522, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4020788409904052, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.28599643357892673, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5040359554493156, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.31290644634463044, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48183974715675615, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2929916734973674, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48088316152599886, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3120625543688931, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.49617263318482635, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3648098913192682, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5125064136233441, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3117704018047124, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.49192558483985005, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.37246426676247424, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5209584150532849, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3262468941551367, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48586000819359126, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3262468941551367, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48586000819359126, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3725023982012085, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5122161929575203, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3669823180697858, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5161342210942241, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.15122975716794776, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.38379689700174613, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5441603162109487, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3683384333457243, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.535354195733138, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3747706572497648, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5209117920230769, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.30492393156823283, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4954261476108242, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.364284960767485, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5223164970771063, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.24024632160930773, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4527249312450521, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1031071354905375, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.40879569940654853, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.15720527174368745, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.375220686806908, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.19598591795373435, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4825413460017427, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.09490574585599613, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.38652552310013205, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.05866055921523065, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3771978909827911, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.06799395054035348, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4163550141836907, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2240898502507552, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5415491600496339, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.12258998275054492, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5014302475974287, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.15984232622995367, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.47596521065582126, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.05266885854027921, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3551300147357464, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.05719178035180127, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3600549294506989, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.10585600619046985, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.07847318517164766, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.13851721298930605, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.27645966460351457, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5766041891106223, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11651389750816872, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.47506935582480836, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10468075025780492, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4004016785171292, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.29817955693860293, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5420613611826939, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2999813280866963, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5482034617789758, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2717321001858494, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.038280866664809454, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.06731462154808254, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.39476633322320287, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3033134628026753, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4755698162289715, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.012770470304307417, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.107571889368401, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.23618922547203738, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3941806817944268, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08589449352149726, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.27606498698754317, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2090466302287333, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3818993801801359, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.18134669659602926, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.41766733780408843, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1536201950485081, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.39433169171016624, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.08333580646188825, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.07595651689900781, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.06962441525660756, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.0035612535612535618, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.0025237297858549763, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.47556050119224164, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.6011398608200079, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3048688483989491, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4231107190425069, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.15204349869646772, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.35443548276779535, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2582643227161482, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4622766760642943, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2130807529115382, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4585809667123008, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.12498291516147136, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.12312267504265355, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.29443275863324925, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7017829861193574, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7743327021667388, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6961795371760597, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7859480663394858, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5643442092080923, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7005543453411931, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5432312750246535, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6677259864784132, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7108042922925358, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8180084374898081, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6021903435236307, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7189230568243182, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6837528314895732, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7968789890147058, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5810419951447446, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7223623051132819, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5810419951447446, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7223623051132819, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4391684160269219, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6371098202414471, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4063427008301977, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6422753361781052, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5124564255504712, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6584075128969283, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7191192065120268, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7900451518124424, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6457054670434149, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7698170823293852, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7555875294328935, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8049022687045564, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6443411340522405, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7335999563315522, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6178921921090218, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7038448765193518, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5127683744264765, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6392337103594719, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.2285369650225378, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.4750387664265888, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5975003598259766, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7683913390959731, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14118350058219528, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.20431837779877604, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1811004938014804, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2649993136544717, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14089011087858522, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.21944603811527294, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.12501819027374758, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2634990040622181, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3107963896402511, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.1887796230243076, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2360941227140328, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.35939098278145853, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1700831186979049, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27468331002901497, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1700831186979049, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27468331002901497, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1273192735797341, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.22231961416584312, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.12807695305878491, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2077034261476462, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11380706349927083, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.18741202960919692, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3487145358887869, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.48564425156445185, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.16283600677994822, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27435920896036364, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3360376952328008, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.35297640449956286, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.21687218788036394, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.35659125027777805, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2652905482508091, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3682977696924544, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.09554138026891966, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.1017839169529136, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14549060082020032, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.22054620758680943, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.20721924345714232, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.36475932190367044, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.11386607947762988, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.33564583347921473, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.16862356321891248, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3637462812267946, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.1485432117087218, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.27594605375708126, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4266832189474551, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.12106878595868109, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3192454012719998, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23649053182388327, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4127382174759535, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.1414434097479761, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.1392050630226846, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2392792151449317, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.388678103641788, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.22356252878437638, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3697725657006299, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.15789014160632847, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.1269046173814566, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3259738911297118, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4954841706551886, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2971168748740452, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4617842175733257, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.34101364633474157, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5758572581135913, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2026639468552004, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4471011187469559, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2826834682529912, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.45013583426187376, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23193857266744913, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.39408808540478185, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.11622323415479685, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.10826694406224016, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.180048782148418, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3772586334343914, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.46442643702863534, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5519480629125156, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6268941789647348, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6958291103494518, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4554740717077828, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5498766350188072, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.35817810808590844, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5012707040525209, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6297960258710876, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7117676662366008, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6297960258710876, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7117676662366008, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.570135897056151, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6801332690579707, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.48202275489653057, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6179256582013561, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.48202275489653057, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6179256582013561, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.349335635815966, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4827709277987172, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.31654831990661464, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.49081221368735334, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3145581711998323, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.46884369852228663, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3947812939950854, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5373384617862703, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.570135897056151, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6801332690579707, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4692880637764782, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5773610754678101, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5796814083647206, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6364369549208913, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4632588853163901, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5787305109374016, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.44382744118389234, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5238682600368207, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2985280444159845, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5072627289039213, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.49402195020645817, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.583821485566765, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.22837680015088951, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.44164180234500505, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4151474543103342, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.638952468710771, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4355097603079957, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6511365998081735, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2468185992183292, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.46792167630295967, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4295348440736816, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6231131340408064, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.37475590201160436, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.549178868228435, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.21305368975019265, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4371748197696026, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.15170197126996135, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.38724812547353094, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.16829349191968618, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.45156426303210995, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.08919951949408464, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.2986174009048306, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.1410465419512601, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3956605149834367, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.10206140509578326, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4176763688729275, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6124700716856484, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4321664312116736, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6410028391476785, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.38791552573256816, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5723637874192081, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4305675865000082, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6312508299648723, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4305675865000082, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6312508299648723, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.004789272030651341, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.011973456545827533, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3002149853465536, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5378189160780977, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.11634129390828839, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.31530902302000635, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.19544795798162903, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3835451743665027, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.19889333501994313, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3885583772632557, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.24480102898506534, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1768354493171793, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.36843725720782866, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.2623806581920467, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.20876900081884944, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3981381071356935, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.21782367859117502, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.21355445282160365, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.1582263258709324, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.09477657379758099, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.2985135749646211, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1086652235986575, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.32118144231225637, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3184011333042053, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.475779589579386, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.18408707168815167, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.39359335046927674, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3530704022752377, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.521530381948501, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21574854574751035, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.41940323708656974, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.33615439462874475, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5097369506167734, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.1441526877675797, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.058854097785805734, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.17240019222052141, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.23425891587078498, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.359355103997122, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5589602235417395, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4267520229161, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5518115366540288, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4248870612387681, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5641041633033193, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.40429429626811253, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.575799986766, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.45381532807317354, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5943177066932069, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3877240689639599, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5570859361697285, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.37917766663411384, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5365794450039074, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3166333840532722, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.48240256356216227, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3166333840532722, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.48240256356216227, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.23329145933277767, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.44291475401588093, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.24227648418732528, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.46146827574639326, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.167208802961431, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.3830062023934698, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.40977628070530747, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5623921018498135, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5197186862359199, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.638763803741213, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.30626379803308257, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5077543267123376, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38861707449775285, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5432656354167995, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4014604107110108, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.555936399533357, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.30924707690051173, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.4978251800547365, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.17706333085447226, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.4047932836379997, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.30904104300309865, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.48677056338263186, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.35551034193127495, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5627284645723449, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5039752490702457, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.613669501327356, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.36932295883897953, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5524455184773474, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.080331199191236, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.23021641289829473, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.328497880819844, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4983088156516304, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3297358210077752, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.506224157487821, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3221305290185444, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4866081657424789, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.05537847775470663, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2899958464274292, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.05537847775470663, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2899958464274292, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.10563809356628297, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2323275601638909, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.07545740243040912, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.20719964403553334, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.07954107728679877, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2990326103210471, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4592557039164775, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6121399518555048, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4926928484742955, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6783058705579786, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.37818447598700816, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5516941276443429, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.34591973979258805, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5197016245837053, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3016434352360353, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4694223786765916, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.11220790698385363, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3598119301621503, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.10020997712284248, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.16327778043310373, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.24470192769722524, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4583472827584427, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5088535943352446, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.625202596789752, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.562048819850726, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7192054483864224, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5550041554031738, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6554946147279708, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4406896260480816, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.571328063702761, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5530531361065767, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7562385559929105, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6077585258730265, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7400152006566423, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6260375038358343, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7803415401430737, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5078162248208812, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6905875293089103, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5078162248208812, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6905875293089103, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2961648173595504, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5022745285039809, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.42144206716572813, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6448871869422788, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.29731554668582794, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4888827115549278, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5803184114968359, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.759870828515734, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6359088668046915, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7818086763650907, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.37446819995007063, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5965995710194948, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.47237086893932345, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6521003933528818, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.47237086893932345, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6521003933528818, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4311779921348334, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6057676750393428, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.31867018346252723, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5261433842307197, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.709255033821849, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3941975148525721, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5191046479503385, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.262633940062176, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.41923206553744197, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3850172427136058, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5264633431241114, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.15363234192450648, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2697691812908914, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4379048206045949, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.251174652769276, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3146726146646545, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4709531555683, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.15413963411151027, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.15413963411151027, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.13978782442553714, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.15182422135400298, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.07543938388328403, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.1621827388698608, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1898569805320716, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3803223837566382, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3000233133055524, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4363867386432795, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3223419048219805, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5205977846006183, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1764046491640527, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3464061249457313, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.15503233293760701, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.08435396018831114, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2005359551536709, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.18856799944599728, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.20466701735848536, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3025868321081519, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2618161850312308, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.46946589430056646, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4395347891601966, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6124294442602769, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.33711507396378565, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.568383173179082, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3222423455530638, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5643748237802169, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3260557929227487, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5464327822869444, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.40332947519159895, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6228862504867423, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.44898438516407524, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6143783254714975, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2512754000899554, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.48284061818613055, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.30916859703841926, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5135112084289326, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3688091032179454, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5618587771651018, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3586319156181016, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5648853941150953, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.09472381928564721, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.11154711865013102, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.43155890347066467, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.619009447565164, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3065593460722296, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5311466716037293, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4918904748281632, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6551168488426827, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.1456085160245154, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4152567008092657, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4895484390664816, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6562187218599307, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.33823684808781096, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.552151899411627, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.30284835181827113, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3991070933698779, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5925781167136664, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.13139413594401378, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.2490406851204271, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3112317271723676, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4361597730424806, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.36717349445307196, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4938275160496472, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.32679491753274487, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5061357551531296, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3784649355444829, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.47122443560931077, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3958704329397872, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5196505496421775, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4850978822371748, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6352541213631081, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.43779970215988684, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5678763862130168, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.43779970215988684, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5678763862130168, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1597896899620504, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.49086962788909555, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.29860454922343194, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4455663313013989, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.19050288241472282, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3175856028332101, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5117916534946495, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6878657354957926, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.537967690201565, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6655488114403648, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5420104447784688, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6785083781968722, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.36033300506928556, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5012711439020835, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3603103614264621, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.48642257026995295, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1717511667481313, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.408433531395965, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1975941306622024, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.27520597189594015, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2983588344542972, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5041326432925124, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.39997687282627975, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5906362815628093, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5208833700498166, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6368157603637512, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5248317090186142, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6599904808886127, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3727105527986878, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5475770179024447, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.478854281434795, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5906564991706454, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5354397296450966, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6627191681525589, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.49612267717096975, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6218353723304708, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3857808912695531, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5169273955057163, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3857808912695531, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5169273955057163, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.425433767253164, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5818873909634904, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.34959700947178757, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5356888229062392, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3818308290157094, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5561897012107097, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.674363352915248, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7903753469468177, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6000288091649221, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.742950065256247, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5781534325005774, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.744306267545875, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5809669142768361, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7168714328499641, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5248317090186142, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6414304239299259, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3976353643835253, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6037335600385767, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.21025696416672812, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.39080193524562357, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.43929751176084064, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5889147220911218, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1743988338080954, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4684683280769817, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3335763231736967, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4822714438205533, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.24628203589181794, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.47490747232624714, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2865635502271963, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.43207538722163397, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3737090685822519, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5762937357995392, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1148153812028893, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.20549791555765032, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3501847839621347, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5180344374850399, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4105639021889742, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5404388902987453, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4339080813601068, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5601377134953289, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.21195371406845798, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4061072764676573, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.22094967664887016, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.42763903484460886, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.10289124253714341, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.20708037890207712, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.355480478065782, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5288950976571054, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.63483775562831, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6773728017430378, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3483718729405163, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4980927055323402, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.32488958976180393, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5442618574958996, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3357171510229708, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5153790879430198, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.25281168697394946, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.42994528157525946, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.11781301843777481, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.20219186255257193, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.35111125142401484, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.47360088422177105, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.30485765641951534, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4770499606054267, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.33469420519942356, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.40802446160905737, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.4747315561546192, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5626366882998202, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.13084917716157846, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.5354938906263675, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.635082221784033, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.44404782758976735, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5596520713104719, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.41618377742781326, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5456804815374756, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2248526055752078, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3876111278076935, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2248526055752078, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3876111278076935, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.23360210277843085, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3931394603219493, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20737479056525865, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3654501418969675, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.057847968205097945, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.09239794083005971, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2977932227461586, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.45438903925756086, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.46773223798622254, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4647428083266434, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.22256734278223791, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3765773373060594, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.4575089222077589, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5374740662953226, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.38366559823668656, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5374740662953226, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.31142819692835494, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.45383015002100824, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.05780839041831641, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.09190080998528566, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1704823945286264, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.33422996692133256, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.249036269104499, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.42116420214640826, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.46916497710648375, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6210364770630794, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.35346737856844224, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.46419896019347673, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.05654743603405948, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.18840545240346762, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.49297132192603577, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6254707347799899, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4017730386568173, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5748162160243933, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2719326877457978, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4943569700727416, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2026214534196293, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3813079901484506, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.19111765019965316, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.354899732054626, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.09775732366013794, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.20273747118892996, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.23026081920559804, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.46301227127595196, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.13065113298388567, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.21708673939419376, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4570682779614497, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.604396796818713, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.38063074910847605, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5580442930261992, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.46418492741290446, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6061288560408914, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.18865524528994837, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.43910447154292387, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3187378316273493, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4900083864782776, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2431364795864718, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.44603256525262225, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.11367986929580312, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.2241654517232526, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2786526099901128, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4227880339868615, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.17361047672608262, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.39377589303767235, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.12646071698454284, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.35399465579414496, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.12760083087161012, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.34769412669125294, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1006991958878112, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.17451411450550786, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.188452798788253, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4226648432088132, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1696179558586946, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.34732496665446766, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1513162576311821, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3665181321185458, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.217376398756242, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.24996060380547028, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.217376398756242, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.24996060380547028, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.10731205149587686, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.1863606234709251, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.09474578264934634, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.17340039476868216, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.029780953159454848, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.17166852645504288, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4562694529579096, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.12110334922926674, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3845930521603701, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1751636962208055, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4465249672703667, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16213942897865444, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.42390959990523525, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.12471175243586738, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3393879612099294, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11913648728109437, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.33001537848010537, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.08856387214544856, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.1467534744121305, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.18599419313246654, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3092478316768669, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.5294442646627652, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7281375072835307, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.933651069586263, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9586507529693243, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.933651069586263, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9586507529693243, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6337520241233826, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7734740773636255, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.7096224667917136, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8862932371217843, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.7409995286953545, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9017022389242945, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.7096224667917136, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8862932371217843, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.882190724997149, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.943123392401343, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.39793093873955576, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.6648788692343665, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.7147882714185101, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8408773556139596, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3359230828063256, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.573086119969458, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.7106361351765512, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8390104107504974, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.7770554539970614, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9260678176630538, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.8767740197085658, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9055624233154097, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.8627586293513119, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8964369716535558, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.9082489095559809, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9677853954871374, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.49475425785336474, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5906548177852229, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.509958011324736, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6038542862803142, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6369088066655332, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7248557877146983, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.594816243433451, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6684517153270552, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.43563519746741536, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.562127347302261, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4178102248624072, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5541365812180158, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5425651337252639, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6573851660329229, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4378498065475581, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5570867906360765, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.516681983326779, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.645063041588047, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4504787313808907, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5879031108750592, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4231763152174624, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5646316458317165, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3242957438175126, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.44238355495975834, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5808022163810818, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.662799816502246, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5847143752213874, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.667787009741639, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5267859045712694, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6664055100184414, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5090592077494646, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6898128904382637, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5494728224972747, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6505680718898761, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.36981912815060275, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5379681557823732, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.19294507404030448, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.20343032850931325, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5464960726645379, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6338335574700596, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.29458137881791246, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5492390632020873, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.154638418688186, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.38427876360308916, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23665785333710115, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.38562451484470484, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3285020660210441, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23590666750948872, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.476513874713239, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.11918572021577575, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.42346176272501185, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.18467608126336754, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.46127619811207604, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.07498804358507438, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3224295470390459, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.07470955153973807, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3255729228708695, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1164634565396885, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4145923720314824, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.18799927787192594, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.1897174995868195, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.20303479872521724, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.499471239852535, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2562052802049487, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4919666752433529, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.16382363658413054, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4680776467877379, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.10184169068088972, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.41112160104491985, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1270469747619846, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.43900404845131774, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.27749477998326616, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.09802074842275396, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.2574156136422799, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.39153918186476716, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3067124925928069, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4473439946126318, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2822493397640795, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.46507913833761805, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.41902736014327063, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6029944827947636, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.17367203300247086, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.37144616993784235, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2129735960909034, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4468251761341622, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.15654619435532813, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.33610131630894263, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.1379310072046867, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.32409635064062775, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.14502740485318713, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.14502740485318713, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.10645321323333119, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.10163680597032436, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.12096277958826776, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.09991777681092474, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.1480417518140296, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.37812113415438264, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20983539712503216, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.42806652596319195, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20341288916638242, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4150437746025893, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.19644453621831479, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4060267989033577, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.16666084560231476, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.37466968251155586, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.26352481475305845, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.42508029689256477, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.11916670082698816, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.16885523091496046, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.07336049608099318, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.292435357035135, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2753456537058715, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4157637470934354, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3360301095319906, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5015691430360719, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.32646109535361356, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.48381777748044785, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.27612097589294854, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4424892418298757, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.39819019648793813, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5022380875494022, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.30042999090790634, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.46930807317618495, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3925406773051543, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5373872822631721, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.28379653782470426, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.42758189890017045, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.28735436056367314, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.45643632651343036, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.29649973924791995, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.44586209023520257, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.27124587961619956, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4127186603775186, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2738616869466716, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4556817348961919, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4053606506369619, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.557889530040128, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3563341748486736, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.538853156704761, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.43788473639376585, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5875237951474706, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.34959513901099026, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.47278445023007715, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3448260128141926, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4979112231829977, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.16350681949708384, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.42520459556859463, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.19367943681771346, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2703053606018132, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.27235655766695105, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.44776972516245306, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1138894686892089, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.23532055968260987, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.08049386277412464, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21735060795559732, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2956525254279143, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.10413677522340241, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.12526164583036564, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2842745976160273, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20293026537059208, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.11502119605241674, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2826072681332473, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1944112173028356, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1898118992024418, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18905238632644572, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20943523270839587, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.09252846219394611, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.36286179116082984, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.40065324863994456, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1584528066157211, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.22740112117788341, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.30292463087874844, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4012206532714064, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20832178285518554, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21681791150611493, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.15256354608052214, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.11808098081213741, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18837255784699983, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23882935646817824, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.31980378769803924, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.322315347128407, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.38629355287842254, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.24060799092585258, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3958883558253347, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.12188389833426287, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.20788063249150548, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.31368770007573615, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2623758746330441, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.35746220695051406, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.26005633892051505, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.32347988292946617, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.22289219397754548, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3382837811314792, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.19194570483164375, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3171637914304021, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3391071440787826, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4066486585212142, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2791036570365081, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.34479412937297904, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2897781370622369, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3668617746176508, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.34599462014997945, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.42876949366685435, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4817073354488476, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.5422050630644166, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.29222881654408056, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3674990639831242, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21592919809500394, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3174152476126488, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.22282171488143487, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3388318294292253, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.11123469780808024, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.15067692076736147, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.0356143901053565, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4452444343846694, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.5114675834840228, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.23183307484609084, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4860771998642055, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.291308139574652, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.47517712618294367, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.34695219571340735, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5253608470434756, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.22507903959381928, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.453032184620028, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2968580868691674, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.523112681253668, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3360386791401191, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5211853611973613, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21675506796946695, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.44636018244046766, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.14568024282778402, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4239962379021346, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.14568024282778402, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4239962379021346, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.17432712705823583, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4068910882512891, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.145362470339685, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.37199566857516175, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.13462826238682474, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4060253335949082, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21554182396690252, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.44338956524057765, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.39963516628793516, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5955868994654638, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21382760075262391, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4314761328726087, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3047874430139783, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.48536344979680074, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.29755613285398774, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5046099633967354, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2255936469724277, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4396597890461904, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0638707075030316, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.292437776821144, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.24544572260995884, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.45430693560049873, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.35933410857228176, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.48586232132101626, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2697896652026255, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3998510332125744, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24373510497535003, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.38614580002554555, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2866979519779752, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.43288926857590915, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3354179041034966, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4707359468602942, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2698452317086067, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4582070027188063, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3011454888332037, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4262131523304905, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.23240224448374067, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4133384318396084, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.23709961272723779, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.41517687550199384, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.22860205692285332, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3182044233158764, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2621312438616883, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3668283434236941, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2822052107603345, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4198020225738802, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.32727015498952, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.45074320734250733, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2866246702095007, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.43367741049920755, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.32110411465020716, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.44807862406147775, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.27913282158047337, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4260697288935173, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.32329508170352383, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.47345326558901635, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24154624906796804, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.38272979449164946, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1874127686625618, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.27663845749925386, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2593593634315739, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.43271674298316926, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1300236096509615, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.32525153283102953, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.29431947865853453, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44837466661278663, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.21254942319876402, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4269647768540029, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.18418234612754833, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.39266182480545436, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.31289401059475375, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5097722113265488, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1632548713391985, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.31655004838281875, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.22269084768108507, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4278034123121377, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17454130529882292, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4080884742466854, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.16966449414791862, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4003039896117128, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.14520318268031004, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.02961162523639311, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.14450400718516293, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3304287005101634, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5073607253994155, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0943246418621213, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.34805553300777864, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2351948770985025, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.38703230999414506, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.20519183872026955, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.45466354608754533, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2134578088104912, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3859086755695303, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.23713426834274276, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.036603349129414556, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2175733312586878, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.445399235565606, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.10154990983620787, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3241234761287709, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.07911223895726585, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3284566286505505, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.31913963266610856, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.09628686982734429, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.1952154860241876, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.19130385778959316, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.38351236751442097, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.20061283670702684, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3495758280859993, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.07998273930895511, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2553179648394861, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14764688052496655, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3128469009417252, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14500816720191645, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3173242925215282, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.04405264390672397, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.15557624503843326, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.04074555031180568, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.1496552104956363, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.1484241683066219, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.11676877515408932, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3390310485983043, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1479505098524279, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.34511067058207273, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1536989560019054, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.44762901138635575, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.19120817575042504, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.40969250228345677, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.17083517020083475, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.39150735535099584, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.06471498019604267, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2882933467523094, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0646129461242914, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.15283455536341573, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.26314054882588755, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2875779877950604, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.40209911650829044, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3288944381277255, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.44408070821988965, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4114907933318661, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5085164164772458, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2002896040873864, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3388229412593097, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.36008600804379115, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4853098816714262, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.20962095850094545, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.36777884239193975, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3273734953951328, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.47406821010356615, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.284161300598023, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4218648610976154, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2807428198554027, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4058440896280391, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.16680737576321863, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2663384154922808, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.07882543593371204, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.0963282470591315, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.24259122722147283, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3488665575390696, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.43223058781595636, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5066667712634532, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37877689433359335, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4634054470510535, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4740262814051875, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5891073641767389, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37972643305107756, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5113424919950917, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.39706108097932113, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5301051151452268, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.07569680446415558, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0811511315198306, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.09606380022225328, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3751172096292997, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4914945427255551, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.28997498044330217, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.49213353233430807, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.14097078788452733, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4079828299257035, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.13141849076406048, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.33283942813493117, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.15295864444581941, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2500778672893524, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.45494893323174035, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.14376690480628126, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.35572014853539113, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.20100292863011363, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4076276304952943, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11078402685193336, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.30524045309162195, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11463104968465199, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2909861509746846, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.09390757917258814, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.21248157589242364, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.1569787205649601, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.16690910711509896, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.32737428538988683, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.413534200628771, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5332641003918315, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.21322100033563102, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.41366535344804717, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1637342873856931, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3881970983070915, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.10502753986446337, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.36830254024142717, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11742665343712573, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.36563345299992134, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.24610572619268933, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.05267625614923987, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.15350182288880984, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.13553404800740645, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3371278820535014, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.23102354810546433, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4512153003070141, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.24080045866228475, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.08097181036179749, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3053595249968307, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.288950858373021, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12278113602323072, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.28569685113339227, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.09049008739913425, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3899650893074265, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1548512533490527, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.316352437998455, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.15710062654473528, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.18129439798301064, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.15382264097525464, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.13408198758732318, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.07839621745254671, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.1846437553302137, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2622163181697703, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4929088970575128, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.22431793519548218, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.39604227398105574, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.09160060296520073, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.22884503589536276, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.08241796975945151, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3466608727751255, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12134082961666683, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2682674585843727, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2373706275484742, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.13482603731036022, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2697371983386055, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.1387209968695978, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3380551337195283, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.13529314038135454, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.22343406175513267, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.18403324079901667, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3179738040092695, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.1620137043520466, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.13304020859999266, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.27172344687178274, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.16488830630298643, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.10763639119133948, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2286324938333245, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.21562480107796922, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2122236502776767, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.031156779833853843, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.16646420617308932, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.14626163469852646, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.0023775558725630053, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.15631796991907554, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4199470043317492, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11647083703831308, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.362366272233946, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.07727363175597884, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36985472300697503, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.14424504302299884, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3278751518859767, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.26771553177100066, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.37949649974580374, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0651036528704352, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.1687003583856727, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.07132774105746421, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.06271293136511706, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.26651166138562676, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3079971615386303, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4820111161799533, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.28695849032593473, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4998009181545032, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.23469484606770763, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4172389094650108, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3192819492326079, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.49617011044543163, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.25575140811008257, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4498199143602961, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.38904911993741875, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5272334688781383, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3366798594244885, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5032290575942354, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.24552764013707506, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.45959682937494845, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2937994669861426, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4721695544802295, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.28514520814329086, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4757962294633225, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2557023064185815, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.47341372742401866, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.31309768184871206, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4792341787454904, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.37079823816873486, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5308246783220635, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.26184129808474554, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.45395719974451465, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.369512066317937, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5401956749669948, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.26656105817789677, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.46879180441648755, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.26656105817789677, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.46879180441648755, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14794205573193786, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.36475095585467476, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.10174226364073938, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2235019520504769, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2648080421287714, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4674196289628547, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3264083012851069, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.46032850662611646, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2593432509712634, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4745626718142974, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.20160065184355866, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5098889524317596, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.23981955551135148, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4808731682191636, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3308717914450874, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5800788400879513, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1666398736971546, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5129077754414282, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.29614367235735506, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6045301048147214, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.13471075888991113, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.28432329395160805, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.13471075888991113, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.28432329395160805, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1432084252186392, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.28641726287478714, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10515245723378963, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.21833110323753446, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.13817567422545388, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.26195281597782516, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.4449695860343058, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6926365319460404, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.41135090225869647, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6201370795994968, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.41083224778511057, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6633295106886236, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.4113791261919629, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6958747657915029, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.36285371273643874, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6272308931328329, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.092853803518812, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.33364983045013846, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10570785968335994, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.21198045114345473, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11368320018193068, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.35732310520280736, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0832791679921855, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.2503889973495181, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.20368338136177952, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3653296593218242, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.18108719755184957, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.332537347823435, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.15420338050642002, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.41396539477086286, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5525295779105852, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.14658698509712184, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3019087046443289, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3199269653277632, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.46348573637808615, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.17066150633798174, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.17066150633798174, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.12255408397776268, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.12110468618322316, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.11216011726678803, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.15706190845355475, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2065671630912018, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.38660038914038075, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2960694463333958, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4881747008412317, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.24966103324264236, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1657794581694396, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2349230687077016, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4194990055964544, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.03494730820037606, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08834844971867042, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1986615588572577, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08728152780371878, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.33571000196089057, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8761560783209453, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9484564543183253, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7505336182671021, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8401910628269498, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8761560783209453, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9289416300153619, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4450050658086207, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7558874882119336, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8107492451395732, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.900032747778274, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.24688498672025874, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6300112897041039, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8107492451395732, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.900032747778274, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.4294674116452206, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.4294674116452206, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8761560783209453, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9484564543183253, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8761560783209453, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9289416300153619, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.41682189465797687, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.782362930596065, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8761560783209453, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9484564543183253, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8761560783209453, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9484564543183253, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7406375008540003, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9160988509714175, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8107492451395732, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.900032747778274, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.16195570128532405, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5142740245749214, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3132252321342574, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.35025412310639736, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6825372617659788, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13453927150397377, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10522974272748564, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.22055493694673897, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3931965048763613, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13755274871304535, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10397715306705207, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13899941210887606, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10947303419437356, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13725861056573663, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11147384852362276, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.09122941759796505, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13725861056573663, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11147384852362276, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.05194789152811301, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.05194789152811301, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1350501875730652, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11147384852362276, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1350501875730652, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11147384852362276, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.06821148611313624, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.07933317425857943, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1350501875730652, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11147384852362276, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.09408024740752835, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.09895358918308976, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.07839951405031013, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.06261389497098568, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11538184104597694, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.09204268041910899, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6885326214539055, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8229812189228393, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.839587623092576, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9096086668952811, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.7267072830982378, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8396959977515368, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6374950652411382, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6643984252563968, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.760856626273165, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.881580297011256, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.760856626273165, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.881580297011256, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.839587623092576, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9096086668952811, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.5054091115759235, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5779798191200329, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.5054091115759235, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5779798191200329, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.5821747317554493, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7539119883011114, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6885326214539055, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8229812189228393, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.760856626273165, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.881580297011256, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.5824621545691198, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6375144448777752, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6885326214539055, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8229812189228393, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6885326214539055, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8328652216139806, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.839587623092576, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9096086668952811, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.839587623092576, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9096086668952811, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.7178970818142898, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8295858852824634, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.251696695878184, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5710821658681214, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.7498810286408993, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7886148242134857, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3480442076026084, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6142483232997242, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2861853478258715, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6401604432917332, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2861853478258715, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6401604432917332, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2852636439147137, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6732018003142922, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.18409929989356164, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5294826055875641, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.26529518334824453, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.596699960316198, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.412295470431275, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.705800771033924, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2592170537135687, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.48962631520102895, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2592170537135687, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.48962631520102895, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2104783778565715, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6117499551501043, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2104783778565715, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6074381660797843, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2371332024655201, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6388309463070028, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4747354911173249, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7360286800047513, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.19850823739068116, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.545876357155442, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.412295470431275, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.705800771033924, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.589811312024197, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5838763481839316, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.18951629567590741, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5476491102899993, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.31072931460421827, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4306285422638574, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.17401517708317762, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.45006261596496794, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.151240443751577, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4224869587588239, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.151240443751577, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4224869587588239, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.26860011657329247, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.14172292406325543, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4762857001428092, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.1435622311718879, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.45714671497681403, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.14172292406325543, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4762857001428092, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3022474972507704, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3022474972507704, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4800955244005148, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5401265646908128, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.35123681047474764, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.18482936243672016, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5172215726655364, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.1786870215027556, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4652953618999841, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.16234676720992364, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.48137970077362496, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.16853790965501372, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5242065098084487, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.1581263594825012, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4522083091147819, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.14384023999987144, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4651629740258846, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.07810235385630719, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.10401577613691954, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.32252336426814965, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2028736642487601, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3614856639698008, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2255489037266197, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3954925749722234, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2927057121559396, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4330945753016968, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.18038302998635977, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.320678468026793, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.272143800067929, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4053920465587089, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3124325727595954, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4415757258745415, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21850594525107195, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4049269026117245, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.33278034531051726, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.33278034531051726, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21233470585998818, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3630016390465325, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.272143800067929, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4244951818012383, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21850594525107195, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4173980390626746, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1958598294695433, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.39989578460637004, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.22325877055095214, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38760873730223866, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2741229265391949, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3721657350281369, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2741229265391949, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3721657350281369, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.15573188896329046, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.34400122334184813, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.16170596160446446, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.33805023952655533, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.23398197530631124, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.2929807168354841, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5975595069845072, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6689604664235209, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8010329764520807, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6689604664235209, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8010329764520807, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.14908960803395838, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.4761746966391582, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.30778741582971547, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5260758146680434, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.1935951733925871, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.43667702869251973, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.2466674257522263, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.15912425773278951, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.36849788356327, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.13380161378318955, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.3620746905979261, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5677534942306638, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.684329671666446, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.623977125888761, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7203812768232026, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.23731319709526777, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.47505928950804344, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8787419089273848, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9422733087334002, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3463101483231968, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5237307224806943, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6666935927206881, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7886059879769752, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3854501214118697, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.595779023757305, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.31011575752288345, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5868493159448576, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.19940445989088912, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.4140097710901331, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.1999934463074552, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.30520457148036917, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4113125177363443, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.42808075762838727, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.32685141385924577, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3758692873615971, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3734832062562986, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.383916695249631, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3804672236690253, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.433708341935832, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.41719958093258547, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4623764370897186, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3734832062562986, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44543323722408085, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4678134833959513, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5051480556620123, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.29528242415723854, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.33278285164387655, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.19850823739068116, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3322089542607952, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4028998029112093, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43422338821405304, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3734832062562986, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44543323722408085, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.333388748608888, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4116646457580635, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5894159589207006, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.633437763335489, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.47426640493104016, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.533549979656383, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.46360731056064436, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5726015901952585, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3734832062562986, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43771936994910393, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3906219304241721, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4740791147276099, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.33573064840973227, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4290137254376642, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2041405149858879, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2728627798814474, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.36592034784584504, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6237774736059616, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8500131524897436, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.573764722928549, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.817979859532479, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2320305803246989, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6224956012824276, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.21449459478473423, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6528501353073614, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.22449758011137355, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5326826664261649, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.26697411956933875, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6328956554106696, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.27341185048222727, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6411651849711889, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.20121892469391917, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5567939082957601, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.19228544753133758, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5417764305747725, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4041187386794465, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6888233111124319, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.9086549610666288, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.9538780144669678, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.47629019423691704, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7299685603603432, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.670001214025099, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.876386276114813, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.20891853890830714, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5547930109285607, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5645815242299279, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8151453923340255, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5972046851135996, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5972046851135996, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.15874376125672243, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5342000553124993, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.24570408832734913, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.17470942957770763, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5699365673055954, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4388504279172877, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.808070563320424, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4841156774078945, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.8256726071164937, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8363600587440573, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9912737182609732, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8895260356363631, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9215559912711291, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.6018154975998465, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.7669980679050217, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8482942955247808, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9256238040654331, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.20164065196183215, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3923533979663226, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4212555584968603, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.44264089366400194, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2750774388281557, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.34712156908889796, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.31322885062380607, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3821582738832969, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3286610737142835, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.385722786993942, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.21171273476282318, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.34680801952866847, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.27483211854002193, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.20951428943259978, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.2989889871112548, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.20951428943259978, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.2989889871112548, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3332411632883488, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4039853784752083, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2218501907098814, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.33654368829688636, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.11732201052820276, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.25299836015791066, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4081354056739722, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.47955174657690236, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.606820630365184, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7266797931843597, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.392022469660947, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.48059504328652813, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4081354056739722, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4731088237118851, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3332411632883488, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.39933193113530874, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3627171579166368, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.42265918111012574, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.20642179908801722, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.19178500195247952, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3514233824120371, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3471790743028735, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5354826964964929, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.14528679532351443, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.45626264176882697, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.21146239923180532, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3672220683588613, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.11365352023191169, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5427832684043266, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.406208369292942, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0993195473228234, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4660581946805371, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.25034600728678114, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3123576615501104, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3123576615501104, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.14025775160081475, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.37306669253790053, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.27805272316398216, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.48815941420187975, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.21267746188711148, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.866397551781362, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.9369949537059603, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5278627722123207, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.8154379350117309, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.41682189465797687, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7155178722189985, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.37420316460821246, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6713980677832108, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6169169270416248, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.2823945343575434, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.09520646862489263, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4231985179035766, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.47631009147745074, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6668706097750393, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3312076918041707, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5907489769215882, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5419642316694008, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8375813242343603, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.45069082245075975, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6399673599980337, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3044867545327882, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5152255320542248, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.37251337991409605, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5810872572798261, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.19496249079519765, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3404780052299898, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3216265867489782, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.36313460166197037, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.648844691127488, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.29018963236087447, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5428475770446293, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.26220676436185975, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.40041995342318953, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.33084780351073634, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5879159712556987, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3222538601891173, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5969957309841242, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.7708186875078075, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8284786787443572, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.08603520723426224, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.41785071883461133, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.37793843728093646, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6768016164890283, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3077932519058548, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.175658807429611, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.47157573411560544, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.20217803037339238, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4743589083194767, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.9048530940348648, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.9226314544302758, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4267826722481737, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5025756331454715, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.18331704949485053, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4681674930025697, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1481394578697113, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4346232049071254, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.47931444666606077, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5290208228819253, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.26104909033290696, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5956068369645927, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.446338868007041, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6877687248093648, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.32961432415781217, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4546852631699836, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7654091839521726, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.20217803037339238, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4743589083194767, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.9226314544302758, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1481394578697113, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4278722851826281, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4952330116157305, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6324855802639244, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.12436722085116984, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4638123953882846, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.10008350737965103, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.3399171525144127, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.3267507236200133, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.14710052131359536, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2322531742374544, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.19427446513842178, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2821379316874468, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.30793937214153166, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.39271105518755994, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1928576545653753, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.27080894796384963, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.15875722180934987, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.335313700439635, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.21800193956058223, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2974641182469979, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20828838183973028, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3002418280717453, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.14942927915034346, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.14942927915034346, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2234473632117264, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3517185856118227, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2234473632117264, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3517185856118227, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.07389245013530919, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.25306188056493334, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3181932375842872, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3060737551255425, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20536337741589905, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.23621003955621192, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.17004486924634224, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20828838183973028, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.29855842731164584, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2425056620207466, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3842334002689132, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.14102929105825548, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.16702356077048272, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.32184315197242147, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.8862476419965991, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.9357668560693397, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.5181212746323438, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6637469240656353, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.760856626273165, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.9001274946261998, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3019157872635644, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.46982207493288186, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.439933170526582, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5265527952016648, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.46269559069048716, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5813300951224054, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4962806188414642, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6142754339875535, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4751132438608344, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5331125668806641, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4751132438608344, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5331125668806641, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.6813997516051327, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.7839574900170875, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.7964269516620873, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.8589615670636759, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1365189729052536, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3779992936423843, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.839587623092576, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.9201441893603447, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.5338072105998289, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6564887791688573, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.24343304284910333, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4684960451084745, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.003075030750307503, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.45263535623901463, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5592911781982396, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.49014451735562026, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6491845645828161, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.013542966735554371, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.5784879107039426, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5683104420414816, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.34190945667692124, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.38471892347518344, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.40122658664791466, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5789876781041586, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4005128871429235, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5795148403403252, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.40122658664791466, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5934450566124282, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4499781507152021, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5255804479733618, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3033668865762665, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4694590302823891, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4499781507152021, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5255804479733618, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.20664181816537017, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.323301646457105, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.20664181816537017, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.323301646457105, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.31211920341047517, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4859322738480559, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.42902556537105646, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5591695775882205, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4028998029112093, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.46152639159313, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.5275959726465806, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5562472188484809, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.5275959726465806, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5562472188484809, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4884391791679525, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.465693385480142, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.5255781733673718, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5338694785332231, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.5680635025297611, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.6428616302560459, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.25823077599534505, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.44626329440667106, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2352761275903773, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.47426640493104016, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4991169086641303, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2803950119994004, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.45110582913319186, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2818720423903184, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3950106268119009, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.28433291815307693, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.48867856058755704, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16652408234019814, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4246320308167972, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3013982925179879, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.21314568971111159, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4218207204961227, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.28743011594299434, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.2096484850050787, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.23587428664438234, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3087246122445108, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.32547779910215985, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.43052436336054556, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3239539356655841, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2803950119994004, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.442887905100041, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.21951524426618454, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.42045058593468565, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3807134866446316, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5378980704892395, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.19667812291861894, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.40012121479924007, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.19667812291861894, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3952782445462564, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.33156497804918816, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.24709063229627756, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3607632660254926, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.40533142214730206, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6060585353811423, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.326434800689293, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4480048055728212, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.32594818888335836, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.44761445450402637, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4064626339162435, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5788471953989454, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.26939651839759654, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.49912839527553177, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.18038302998635977, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3896135506969871, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.17793925745339384, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.28012888208050135, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.09585061629230296, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.1893202669845784, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.19923928734822613, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4663425112609953, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3240779549699948, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4812338546765038, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.23384694577370996, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5096772803089438, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6511024507582726, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.38983691387368935, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5816984404013605, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.45873576799767507, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6043854820928907, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3485638068094234, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5963375644080781, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1670445270854116, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3361164827798928, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1845895819969781, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4127769579837372, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.14085916416769417, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.33804825970733066, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.36210097004176117, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5007651303154664, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3875738939089708, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6165609648382772, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.19500507550993698, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.45061310264279136, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.35630548449868954, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4957192173723922, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.24826065966265487, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4805206361807775, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3341317422457504, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5079573405434391, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3861304705880985, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5248223977765574, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2974309561779646, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3992519602378697, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2745762486209681, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5002984561362573, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.15815783405728007, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.29769975373629043, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.4161791450287817, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5532809970610469, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.00869132029145675, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.05604574546688056, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.5131341853758327, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6909093149313557, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6036101600843071, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.45886678012586496, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6644271635045849, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23152888964854848, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4544566268147502, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2819047150780413, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4860988074114069, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.477402596194193, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6645173033113367, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.23324675880179935, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3222841628268958, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.12522096668112345, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.1209593074330819, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.11422068431853144, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.12726932659656656, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3016275716365683, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3029955223846001, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.10593991511157044, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.10763180772579908, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.09759160756501183, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.11968354725525952, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.12967052968787476, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.002670940170940171, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2927796599787371, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.23522291570950735, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2646447028332218, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3535161075143434, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.17785897894606995, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.11910610888409226, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.15764879870902038, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.12596891625474588, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3187271473320672, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5308594426934777, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.20158074753947833, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4601245932152929, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.21951524426618454, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5863542367683318, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3187271473320672, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5195515317126674, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2641917896528943, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2476165058078653, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4867146510028071, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2476165058078653, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5008770061123741, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4516694906173442, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4516694906173442, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.16467029855845897, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4015922868181449, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.15774545980684188, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5404685949807201, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.32916817971873047, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.7541859578343534, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.8925780650702051, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.6028817681965138, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.8184572215512641, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.35412968165085734, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6270889448255044, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.25357054476878577, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.44844165354587767, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5718331963429273, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.48255775311856786, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.15844501337268932, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.45565290753593196, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.031835895924415845, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.030384560195149946, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.052306204739960505, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.06823556261259293, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08464912280701753, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.0668660748745658, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08214465123593925, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.043422322290125444, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.043422322290125444, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.05921052631578948, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.06555059438405589, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.042535290268299525, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08464912280701753, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.09113274429924344, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.0668660748745658, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.09023527188022927, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08214465123593925, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.07647983237297014, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.006944444444444443, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.06823556261259293, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.28479942163807365, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3268532842861261, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.16442902274779153, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2560785881872606, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.09594785034023696, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.10599592327617327, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.14500387607936882, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.39811631946890474, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4004997065707043, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.20217803037339238, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.14407576460736185, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.20687913047075865, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22828954232316065, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.04127554085191462, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.04127554085191462, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3400215619680846, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.33719880338573494, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.26104909033290696, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2722033387175046, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2116210665015609, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23932595221309674, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.311012661607424, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.17923344640485428, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2344967623081854, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2227227312202058, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.267705544827011, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21233470585998818, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2655126465892259, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.19228544753133758, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.14059624172717672, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.06787002753251685, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.14025775160081475, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2329160565767051, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.13714971174966237, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.40286739446153647, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1420515519076652, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.42828528785491377, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1420515519076652, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.42828528785491377, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.31941740500496135, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4712019523587867, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2555184829750068, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.445432191505933, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.31310070795186434, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5511747373016408, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1420515519076652, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.44106281582354434, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.26967784204515577, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.26967784204515577, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.3648139824831825, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1420515519076652, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.44106281582354434, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.32777230310669525, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.21544992729237186, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.43862011357966985, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.17460005233998513, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4006764760264664, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.15234610459458484, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.46726908278200807, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.22817395443579389, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5333512480190983, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.22690068744270425, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5346629648266377, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2696565254551411, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5248534524852462, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.21813311724067094, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.42518332100320455, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24258882871985424, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5303410271196803, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2524885334037127, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.478828996001936, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.47788634915766176, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3299895472527792, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4984179060203801, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3152861344254501, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.49782106997559544, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3617640392425988, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5522465855173821, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.24187339355165743, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.25756580609747165, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.25756580609747165, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3163161243012683, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.23687685391328772, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4980341077042262, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.33686890954009086, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2569984870940298, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5218743639828287, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2504503449831057, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5561372885863383, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.40043666315630655, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6786513775230063, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.18471706734883164, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.47575293285704157, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.18462053544069879, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.47706095305435986, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.31048078917785243, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.2922953334862234, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4235355275892789, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.08644426594013177, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3191159905793865, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5859514292713682, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.5894330056015769, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.7233859304178071, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17509131039045966, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.29735424498602653, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.16638505369603646, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.43509325019402184, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1896632646081197, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4171144217426057, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3276463794734248, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5691582878087721, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17976451428761386, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3585067888170081, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17976451428761386, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.343282119048708, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.14582148798471004, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.31082696401117216, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.532789925402232, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.27501295888248234, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.6880908437029064, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.8057610214990305, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.5446619336438847, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.7009531476065792, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.31142220978542806, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44510270344803765, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.4331536929006432, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.6392185687264759, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.4331536929006432, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.6392185687264759, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.18728674627858763, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3939325010546995, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.1878901082125714, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2690293752604482, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4926185189227678, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.22911003908657962, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.47520559779668814, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3842217688744563, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5778946517730051, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.42396156294478327, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5537191420830491, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4392283615599068, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5797315907567191, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4247462710609875, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5232906543197557, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3588098099835732, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5299274110588972, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3401185071799048, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.46989148838686473, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3595597536132021, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.48077684581215396, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3595597536132021, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.48077684581215396, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.37071912413861663, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5215094709752708, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3530655323510889, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5388344492000988, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.40232211736779205, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5438807582708866, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3395665608660451, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4640706250815061, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3317190808936393, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4513622173176303, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3401185071799048, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.46989148838686473, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3395665608660451, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.48690229401918267, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.25609516769327906, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.44908098526380485, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.22422504713155436, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.22783713906265132, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.38679326840946837, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.10752875081378005, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3325883825268305, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.20583079363601006, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.210765781867173, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2130422726507048, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.14625505122941285, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.20063126619058114, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2115210387013347, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.37360356038205855, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.12597257038347442, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.18700830990734377, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.22271477289353545, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.10459905477537781, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.1880220063294874, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.18813687249646147, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.386314894857759, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15613122185272454, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.42694636550146664, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.265789590051501, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.1777383985636279, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.16149927362386943, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.15221118163644626, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3040820655534371, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.687028746592056, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.7656691936879507, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5948821108337683, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.7754376703404752, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.6740433269994325, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.81875959995474, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.4887049965066992, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.569614552439621, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.7248600507984249, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.7668237605712521, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.4081124128738056, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6001792982263469, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.4354676264744325, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6617572899591347, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.26622044491524727, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3345692380236303, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2665965212441191, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.38231331369588106, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5105137893788634, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5591104189798438, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5502408885295141, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5654268254662816, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19445724895759758, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2659249673909068, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.7092625431287067, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.812789308577739, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.7254204378043243, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.8078563607246445, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.6823528626588446, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.7340217379632759, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5608429423716823, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.7377212542047896, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5184760552547103, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5428419284565644, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.20333448190047881, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.45845403048189814, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1243018504102695, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2432739373207714, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5577288803545524, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6039990179307908, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.40283046047758825, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6078521036010628, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.583899712825618, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6318158012380937, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5721933920005094, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.7452043729061871, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.43434098825795264, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5541452605668559, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.30978939072405803, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.47835270710065314, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.49173653802585443, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5612260220369396, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.47992366044240764, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5677112072864312, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2837655732884958, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3548188785647291, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2837655732884958, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.35108999563681076, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5751167640035276, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.667747434082355, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5303402316424991, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5507521834828499, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.34335742724395907, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.43839021069555023, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.38815593666004833, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.590684675442797, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5792154834458868, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6702416408010979, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5486578343933162, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6828178383434446, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.05060207207173417, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.26022022728092614, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5366441955817576, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5916693427343216, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.475628933599271, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4877017847791856, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.023022429590310714, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.4755160782268483, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5834441686450073, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3875738939089708, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4061202407032717, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.4478039777693801, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4520078853554537, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.5013053504161699, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5258745854532912, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.43310177167002284, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.47137144154052957, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.20330750836901912, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36048721816693735, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.24356042138823908, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.39273557843889717, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3267294026204632, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4333271065990519, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19406071325325308, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3533983915843073, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.22205108445785451, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3592356435419641, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.27213157170702923, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3876323907884819, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.22936436185450496, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.34768470593248824, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.0032051282051282055, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.5502408885295141, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5526384138963923, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.38630936190395015, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.43999811415716666, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3479992308096562, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.43167311437074884, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.21171460625310196, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36791058458941883, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.21171460625310196, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36791058458941883, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.34019506273883837, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.41875873911174444, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.1983704639040531, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.24582153349970853, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.335417686033102, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3669951214641638, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14669686413046806, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4859054130771095, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2034208182228192, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.574929092637314, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2034208182228192, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.574929092637314, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2034208182228192, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.574929092637314, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.19300404208836477, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5580822623950328, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.41837196571723934, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2284240389125248, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2546939135935566, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2546939135935566, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1590542798683595, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4277341159613323, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14669686413046806, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4749329376022692, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2702173841437742, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.22878386498145054, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.626426212930626, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14728212724124629, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48836797124457354, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1885651765184848, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5377638658289048, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.433605176180698, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.19674214866452416, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5589633489315522, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32342498551930216, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5669007627289538, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.1476770699073328, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14757581190431865, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5161370290424468, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.19394698940390126, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.26825696990387976, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18661491233517533, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2813929671493715, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18830095106396066, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.26618195694772356, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.043577915062129685, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2047856964061869, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.32185278974853804, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.42815980887088867, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18818468056723417, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.35937272275747895, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.17339704923260021, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.1992260278488686, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.15025290533149663, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18661491233517533, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.24224327949566424, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.1742174981041678, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.38785611216800814, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5025112453850064, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2706380285588004, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.47250854082936017, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.19394698940390126, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3735791805273296, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2291421308389693, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5494313751991973, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.12607704921829502, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.272446590350039, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.12673718536830808, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2342177526227224, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.19729680466426772, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.1971221255458505, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.09784168213672303, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.29894945474335277, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1333681278040752, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.14453940362467121, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.23375499051160153, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.4978067743410731, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5375886122494208, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1261312269838889, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.36361963826047305, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3444628323551915, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2042128370387497, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3883201120549514, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.19978801989899175, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3566648944161287, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.14189763458782154, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1396681036260065, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.16770949497883902, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.6695580814326164, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.6418894961106189, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.5249562833679632, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5698312265671861, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3090705808198716, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.42787161685907876, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.22986864711558166, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3934151437056127, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.13309867982541607, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.12013269496147223, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.223476690880495, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.2246029757863831, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6417603075499863, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.37709297891717664, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6881502501430368, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8003203203844999, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453478043428296, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4765874091118851, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.45911557772276623, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.45022125383821326, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.46874267375238576, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.6350593429017282, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.6022395694696409, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3407065041529668, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3482814151315599, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.7215691881328408, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.735100789804592, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.6219720158712322, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.638758039725182, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.7215691881328408, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.735100789804592, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.6517181973179901, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.6481167033801164, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.6517181973179901, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.6481167033801164, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.700487718300918, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.7205373993220106, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.6219720158712322, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.638758039725182, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10143591215942639, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.611843760819802, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.6194911484836914, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.5796016058049601, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5650600724216098, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.5894567062209923, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.6051783687131701, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.5907010930652489, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5995581839975431, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.7215691881328408, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.735100789804592, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.286085230494539, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3712901520520525, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.33500599401126563, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.34371117385240735, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.630923553986829, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.6458808155334796, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3013901676230198, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.38106012955734714, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.35187745073108273, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.2850647115160651, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3190905975399158, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3175465093373464, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2028736642487601, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.43458947791319813, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.2614502000808532, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.2614502000808532, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4033902612785559, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.11434800023292974, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3575409421974955, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.333187321272665, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.13598345546333285, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4135396704381328, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4007426083582278, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3101159279982649, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3909330178955319, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.12962472880491877, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.477009194099272, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4077182885080447, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.217295409663537, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.12173115521158184, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3904544509639755, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.38091370416670794, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.540550443602966, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.36314748337164254, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5392658386159207, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2293530951556094, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4689601314620498, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2293530951556094, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4689601314620498, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.28552619466205187, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5197914639547802, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5508290063627067, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5508290063627067, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5508290063627067, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.35459684529390034, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5519360558961294, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.35459684529390034, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5499993547125768, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3820562306791339, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5488313413379253, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.27062395495883934, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4407436716645838, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3711335186021823, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5595427509161435, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2294068720558097, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.40458364050078693, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.32588643749980295, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.32003170276441123, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23088247483586974, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4093450185788297, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23277990398476162, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.41508156849006633, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23274285105688466, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4091360043642453, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23189835231884592, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.44157797833899437, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2324422363331168, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3902749945003648, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2324422363331168, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3902749945003648, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.11917756990194882, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.37850093315889116, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.12901518038350407, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.42910669735129914, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.2185876061269953, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23251355381714656, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.42986991593991275, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23189835231884592, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.430897509663055, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3330732444230803, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23721317187079113, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4319465813689286, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23189835231884592, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.40563324637329695, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2403479325641683, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.40502552058528674, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.29417113956364643, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4653698220842079, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23088247483586974, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.42828303349678104, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.45237912327122276, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6299071573751139, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.23736810439041953, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4004852416401387, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2916261378761629, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4106520926894174, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.282764733088686, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3743678965131091, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.11008681552948653, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.29720349300427057, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.15511550090520096, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3922184662482167, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.31430120091187586, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5013155459452984, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.24715087322306514, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3982414931184515, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.24715087322306514, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3982414931184515, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.16451929399933107, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.2957279302594959, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.33926500357187594, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.518547841500169, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.17923169300061667, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.10793583834163357, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3079497311888636, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3049259527424873, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5152417158067153, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.11401282249739858, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3117911565455793, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.34019506273883837, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.48708558391259515, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.32857675712890333, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4464566565029437, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.17260955718893642, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.33184166448858593, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1676136890247661, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38914692664434314, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5605065818946205, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.586853267829013, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.36300296341860155, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5816676674074003, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3525399760372503, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5798116969849163, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3927053212677373, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5108598154804425, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5369357392301045, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5869601651194081, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.32163989714697483, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.4414323713243047, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3722001929300059, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5252698638532942, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5369357392301045, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.592567167759071, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5369357392301045, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.592567167759071, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3514475288270508, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5361569875660316, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.30653735217115763, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.47019788701989235, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.502115172633202, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5841884402878015, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.20913838136220486, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.40960094031121963, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5369357392301045, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5869601651194081, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.27914759735007616, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.3958350231734361, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.20974733068050955, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.41455868084196934, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.20913838136220486, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.40960094031121963, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.45729707612649767, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5446642967099489, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.16086531618356015, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.2797876941198672, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3277803741755935, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.4267708983045122, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.28765408533715414, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4046608868073569, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.1819722649161304, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44254730215235283, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.25291831689404154, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4482360279074225, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.279600269133294, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.48172049854477195, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.17087214948464993, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.36469648037819463, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.22872196013470597, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.45089857576633846, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.1258907882951215, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.34143648068854054, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3312427799844288, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3489311423593648, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.11986809949741643, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.34629467658248214, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.16978008124086652, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.35898786835400787, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.1685048160073683, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.17550354183836317, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3977547521857469, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.18910054845801366, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.46711157655346974, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.32666181171942305, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5670457942911707, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.29175929784144866, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.45299010750030405, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.15919612785658785, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44556760211080115, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.30531851995191167, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.24463910693302512, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2908660541001102, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13305199541830684, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.43244987270004115, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3377385620641691, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5256128450453542, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.44776047557667586, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5801193947715436, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2875583820017638, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6087635830564418, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.356937545593233, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5492415189153258, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13836903384315105, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5516548411073219, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.28295596283263513, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6067794553589253, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13597796343834895, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4484665724193764, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13597796343834895, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4484665724193764, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.20863283213455547, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5109257435313587, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.14153945350617025, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4466955096469747, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.14785967807080633, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.46460090410941435, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.34589895849033103, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6136307264772042, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.23321078701700157, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4758513477167604, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2810551683573811, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6477048453606161, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.473265686519562, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7021422985630228, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.473265686519562, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7021422985630228, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13072010980679707, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4862878243251588, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.11810019511256618, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.3708545152745943, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3423375720396189, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5343801172775681, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12546912767038895, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2651343523961406, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12407216162020399, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2664864612493293, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.11261597894135422, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.25234827342962907, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12757855945289526, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3385577201847465, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0841173493088763, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2901271494395167, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.11556653761629153, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3140069931838876, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1175771442804648, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3103572690939351, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.30248425155787256, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3090152221044926, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12629279972753293, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2933944065312711, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.08089898227976655, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.25718236707018105, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.19563561963987236, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1055629358593665, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.30482671461107386, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12508519872397364, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3057389264653955, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12363251371327445, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2692822154793075, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.24470651147480013, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.08535078026464633, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2981048700438665, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2776405456134286, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.09410612421964877, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.13696035837771334, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3335388002918436, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5322520826224556, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.727131667480615, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5266403878479265, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6838125749299477, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5276151436342643, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6871514991080862, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5276151436342643, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6999124430022288, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5322520826224556, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.727131667480615, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5276151436342643, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6871514991080862, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5322520826224556, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.727131667480615, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5276151436342643, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6871514991080862, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5276151436342643, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6871514991080862, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5523722682139371, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7471196627888963, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.49611334615935637, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7296403081651096, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5276151436342643, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6871514991080862, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5274964121279998, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6941952618694388, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3763278728427448, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.47453622408885904, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5523722682139371, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7219229057874782, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5002744991426422, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6429454824803486, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5523722682139371, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7471196627888963, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3213275671595753, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.40961777715484393, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5773184063472755, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5331034421473965, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6806929097519565, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2092659579124333, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5354766759595367, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1284866896836278, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.54959682211865, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3099627272480552, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5376391724348849, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.15742483335373852, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.43519517439687405, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5074919773327776, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6528956124603694, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.32705341718250747, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.631354608587055, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.6144246566045058, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7550732449201221, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.49582717346593747, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7377780892834709, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.49582717346593747, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7377780892834709, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2238855010644693, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5288881528593262, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.06295028070151909, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3271734324151627, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5831654195482086, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7601444481236787, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.46797289640794176, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6053337914448172, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.473016146288238, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6981990328342826, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5023049672447087, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6885140390468562, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5023049672447087, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6885140390468562, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.33638190436371745, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3649580097673384, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.45686283928900234, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7163619637625416, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5703017172567459, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.78509136371851, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5226605904538532, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5272140519221666, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4692685009782657, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5107231090800101, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7257353760607679, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2680165156355779, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5590529072823445, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5470973834864862, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.36023811550441615, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6357024906157128, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.36023811550441615, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6357024906157128, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5563318425026342, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.45238747470939605, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.46536973216841626, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3200938205435179, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6393945963053513, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.38037736789549603, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6906084512101429, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5478041897913022, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.18882437844970767, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5789754712947318, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3200938205435179, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6393945963053513, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.47013511859874646, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.43427164452809086, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.526079635392936, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.32001589569502475, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5274343388526991, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.31869191523653845, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5973293882694002, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3128418715354195, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5961262622141211, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.302221525161365, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5926217012511299, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.289331164128846, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5515215768338904, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.30470915491420003, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.542875812219914, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.289331164128846, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5798018459101258, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.26144021961359415, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5270061175207554, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.26144021961359415, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5270061175207554, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2994985311892038, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.611702219968759, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2994985311892038, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.611702219968759, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4376035090962864, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.312793730905921, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4874766693766197, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.41841993715998216, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6644204176723965, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4259108629005092, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5685406243620383, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3162277660168379, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.533113142157349, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3162277660168379, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.533113142157349, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.26596351950249564, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5819860704357703, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.19037861963633804, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5872021106043722, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.289331164128846, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5970102524600497, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.6666467303030572, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.6471929785766445, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.23287896954139942, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.34835288582718865, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.23287896954139942, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3456033257148638, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20038908500140973, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.38365854681342043, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1845895819969781, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.33578716975410133, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20038908500140973, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.38365854681342043, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.48682021841593603, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5363950719917215, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.48682021841593603, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5363950719917215, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.15071676257541072, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.28916309026824916, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20038908500140973, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.33634707243903805, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.10817340917404702, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.6681082569496674, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.7257478469803625, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20105373454060027, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3461597307805182, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.18605335292758288, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3760221461307777, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.5998949116852975, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.6761932468711475, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.48593738187963054, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5468690247087608, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.20515691941627118, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.5398995684986874, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5601040209287937, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3664818394063563, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1404678994830558, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.470059848862195, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4348498215169483, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4348498215169483, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4289684145996228, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.42753415245967574, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4126375622076229, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3892646190457294, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3964051686924964, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.14482189302397735, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.36685295299999376, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.16703297708538037, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4783270379573212, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.2739399901032569, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4227538623950431, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4232731925426904, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.29607319718105773, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.14523626605098836, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.47292367331792823, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1759326236712771, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6193592475350455, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.38894730753477064, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.1915653719498864, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.34479320712524314, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1475256903804988, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.412830471303484, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3097707930450913, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4491537749988506, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4088404017667301, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3026286472844013, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4888814490763881, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1751062735415077, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.441470604570403, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.37429964421261713, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.31505045452389213, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3361093414752474, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.36806833406434675, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3574029228231044, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3835415349913397, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1440453111117146, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4724943996845495, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.30778741582971547, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.44804144802573814, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2744668544653848, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3540230245951609, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2167710345443372, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4369788276869796, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2608721373229356, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4425523567948261, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3771475821372856, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.29089871340115286, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.35722668031235094, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.359712726799806, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.30742231621284044, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.33091815669121233, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1627690505553611, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.41167257464400747, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3111260879051516, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.38964624025381533, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.2919152112878164, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.2919152112878164, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3074764316375467, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.23220245818800425, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.15587413918588733, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.22637791583194047, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.46140916594629944, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1974060384182083, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4392402072324801, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.2876656267355248, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3597494652312718, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3564249821229717, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3526827693240968, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.013937336186971022, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4256815035543486, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.25381494737245897, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6023865926498774, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.20828838183973028, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3919127720212458, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5056837352118368, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.21800193956058223, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3968860255103736, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.378786561257948, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7119470941244537, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.34537865578685034, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6888865426349207, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.499435958665741, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.35788354361456914, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.550328705070924, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.35788354361456914, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.550328705070924, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.2612013339983373, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.2502511779218986, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.11104601968657288, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.37257484093951504, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.540889451315855, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.35597394633234813, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5408630324572982, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.2910873658777246, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6726279357179137, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3259889346257788, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5117673950877254, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.21675453206953177, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5731679833174212, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1423071532720465, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.35461510790456463, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1531682455208201, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3155588394550809, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5004428568600464, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.302221525161365, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.494647923435533, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.14239015212277228, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.39011057458940945, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.39362191501483834, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5349231274294316, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.136176992562601, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.37233856369393126, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.31913543337589395, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4641046311505297, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3191922067457696, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.46967594996871187, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3191922067457696, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4322938742789178, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.288118595440787, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.288118595440787, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.28416048502946245, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4011088672280359, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.39369193933754015, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5367684135815661, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.30470915491420003, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.45679896683951937, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3792611111696206, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5498654958143645, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3015899197760847, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5407786457967327, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.31322594245234425, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5703202724838755, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.11894772669130835, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3633504363047486, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.31630329237321364, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4566752559119006, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3387725035817808, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.003987240829346093, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2837655732884958, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4099902893843507, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.379527516398695, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5401652761721537, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.4063299618766256, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5674287431823071, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.4216383984557386, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5776987776765293, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.32053532009253083, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.43622106696027124, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3598105144545827, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5180775171589359, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.13877365047234683, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.40018004900198584, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3312615528522037, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5044209915579331, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.37059119553219877, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5193244779395523, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.0963782232238735, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.18239905452001884, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.42530943703228064, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3424536495902577, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4759175045802691, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.19988815653705452, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4045022211830996, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.57703623574782, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6448162735306054, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.5596234868159183, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6146584645720056, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.19839774013808123, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.42289602914471713, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4036833691062196, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.25214095994813157, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4596858639513775, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3383930155468444, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2514130629286468, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.29615165360116247, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4985825059590937, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2878333693524178, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5587364816350978, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2878333693524178, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5587364816350978, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.16363329713787583, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.40856136233285967, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.14087105852460519, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.41054287635417724, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.29036802523421973, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5539971386602764, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2878333693524178, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5587364816350978, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3642301318550941, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6103580099130892, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.24479879846461303, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.49899959922136505, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.24479879846461303, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.49899959922136505, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3642301318550941, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6103580099130892, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.21993826115474513, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5016488706154938, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2651383005722524, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.44609755185666794, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4419435974935697, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1470815798406082, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4857421015300819, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.489454127538689, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.23769560475681795, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5396996022143221, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2992831985740625, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.276654640985355, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.12030803390896863, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.40343650886859533, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4718372009351201, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.514371044868007, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2167183006379162, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.22719782145384587, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.35412968165085734, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4347460767932904, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.18295654224495206, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.24542641806876497, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3308548466798256, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.41359956263207037, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2204887282071633, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.29000609768684643, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.14962848372546667, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.23352930000467023, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1667955161379731, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.24294928497714877, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2646015952359329, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.31570636967571897, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.23077125078149244, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.287152353520795, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.21538202046194896, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.19698014877442954, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.35412968165085734, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4347460767932904, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2697856975860103, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3242134827269961, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.15875722180934987, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21215881138968976, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.03692675325478651, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.09241677321543408, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3308548466798256, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.41359956263207037, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.15979727306988675, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3237722713145643, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.33258947777791037, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4033582072599889, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.46631004676740256, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2920066581890844, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.36052310235569734, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3813114671801389, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.39681350602982185, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.45701511801046707, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4585873077614039, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.018115942028985508, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.6061105881801929, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.6319310381959741, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.5549270001127403, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.5679891636123928, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21061661601439866, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.25309156506322616, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.22979089497880623, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3353527174512909, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.22979089497880623, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3353527174512909, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.14098829079624148, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.18187234472987732, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.45701511801046707, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.48271019772277457, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23442577260681427, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.285898366238754, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4223157402750782, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.517518936974854, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.6061105881801929, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.6319310381959741, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.46507550803536196, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4753776301541142, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.15756009499054252, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.1917949409166148, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.31748752251344486, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.33242017378335365, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.17567885044803916, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.293234132230594, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.09900753693425239, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.8164795700243455, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.8378701010587658, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3841997815718642, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7084389853258415, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3212854967972961, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5882101692160411, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3212854967972961, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5888103425295602, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1767874865365185, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5011179630496438, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4853620477754487, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7648536899268785, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2634592129280123, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5830409447205244, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3032929624979452, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6298789412741047, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.26380647520822076, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5568746681062378, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.26380647520822076, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5568746681062378, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2634592129280123, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5830409447205244, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.467013157950131, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.74376385639865, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2505523539251516, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.58636964504927, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3032929624979452, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5928831841690573, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.49083010926596, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.8148280157752726, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5298537180556899, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.8227489319779633, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3074203461059601, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6805350756811194, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.41247506600834843, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7230635818151804, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.43000007605628365, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.676922662116625, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.2603279434460069, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.15094258117090345, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4957807154774304, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.46175494867931294, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2460137257692754, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.49701225041511987, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.22229849552064015, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5180400950710813, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4768696920928415, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.14402386030995318, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.47894872241562697, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.340936057128646, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2382939784364074, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5141279222953337, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21688801920091497, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5164502018806274, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21688801920091497, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5164502018806274, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.39139435171133763, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.43354092326762567, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.22060236130929797, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.47227062964235317, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5039471118843061, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.49622717544883765, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21059469740788836, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5326130101027936, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.44503579680221195, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4828640829097101, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2853837110567848, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5109111081376363, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.41754208336163356, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.491135543219209, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.09970617113450042, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4157699695564606, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.25678404806291744, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4451755318490681, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2553868974229174, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.19334524624566626, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.29379118299158063, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5236831459257523, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.16336470131023162, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.42952676125304995, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.11902001907030836, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.37006869202652387, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2066736214472914, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.43330165155730577, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2066736214472914, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.43330165155730577, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.23220198081265267, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.31389820868327617, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.1884575363509431, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2797941128523861, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.25678404806291744, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.47809631145021503, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.250737833894674, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.41575118479921364, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3073899153729068, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.24048179389846544, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4185563869439441, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.24048179389846544, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3887778043362071, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.20178615855419402, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2894670683676958, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.31029223530511546, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.49153218387646985, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.25748661016289676, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5470575132556847, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.5006114305135408, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.7491334025878413, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.22419056820298167, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5391137756687266, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.17640520319198946, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4734108339946783, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.12607162121844206, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4021408353441737, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1691896235111172, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4942911926258494, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13129018476513854, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3768713474616184, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1320400322138432, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.37069186801926757, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13471766853689124, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3119115134466902, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.20910516205585403, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5402831897795416, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1664517270460891, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4173599374906763, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.4545984910679452, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.6246203671316624, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.20040945203683083, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5452353998273013, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.3244913214932798, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5736635347103882, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1333675348352632, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.41536428053084135, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.15949080497053747, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.44751332637022834, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4451296305423127, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.11503804692641476, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13232291594986312, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4925850413196293, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37652399404345116, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.42944002472700066, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2833048493206313, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43070982670283003, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2833048493206313, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43070982670283003, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2833048493206313, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43070982670283003, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3855945567658395, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4425261260201938, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.19981064492544628, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3919499606072391, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.29041376174024985, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.44402718863249474, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2909755167251368, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3877276005300317, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2909755167251368, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3877276005300317, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3762332646616698, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.44173278869750104, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3612027039755029, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.42754895008207144, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3107474604434454, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.37453928297488676, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37652399404345116, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4474954196802953, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37652399404345116, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4474954196802953, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37845413812632356, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4493430485139032, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.19789890035445162, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3035656856094186, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.27882795137246297, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3921594573906297, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.1741601767923143, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3262568203835466, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.18059957192216716, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2915951586142145, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.39732265306094305, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4578339801815961, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.34973466192007374, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5437131659817407, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.21349332971500937, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.43940628135351467, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.22437887629721057, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.42808989474838754, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.25906260375197115, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4529830757711879, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.330771698935835, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6040822481559811, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19609258298805401, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4573617031251922, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.28061557610476007, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.560457154689433, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2778391283025028, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3612052784705575, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.28199624764312037, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3738706207569365, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.21094997405663482, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.39139474899337623, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.20957556911439226, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.31847789452338926, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.34016424094441117, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5639990181718147, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.25730561864888907, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.46584286350414655, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2308701796614315, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.410716638103963, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.33958660128607676, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.537913519711218, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11579175680314889, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4260038580397574, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.18855406981696507, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4726960575508474, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.10751512066844296, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.38028346418696723, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2516546237169354, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4948297815905772, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2862280732631754, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.37692927868434317, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.18002829271425147, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.403106948979652, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.31961066230165364, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5296986868661864, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2617850444952687, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4734548340984469, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.26339057217264256, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.44366430876981544, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2722704374402053, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4630549375673026, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.08319794225878227, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3214719120157045, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.015108725587447323, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.10794551001487797, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.28456215809018903, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4526033316806777, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.17278330851481746, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.43449724374841947, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.11161815472639028, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2516546237169354, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49035700707239827, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.15723078586799477, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4181020982953858, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12118292800678573, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3757003782374596, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.40444733722022824, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6027382652603281, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.306542338000354, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4638359231061822, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.08619971065255716, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.27348840811300873, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.22517504604059183, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.18555209289044108, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.41750565818533353, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.18592370210838877, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4365745598211089, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5931895310669659, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.28761252282719213, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4827207642978027, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11508711800431275, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4108808711506724, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4700695381391195, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.13254512146117509, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4538619157918892, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3051552202117091, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3051552202117091, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2487541869141638, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2668685259208986, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.11305182785450434, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.16927318970546587, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4389579378602983, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.417766128554039, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.12219667481477892, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2978425654839479, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.358147858289425, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3897036060558728, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2032300760326944, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.03546365219964397, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.262306546138322, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.33626043540904865, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.538764562032814, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2560635441623709, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48856557052258637, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2560635441623709, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48856557052258637, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.255778504657948, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.48897269386714304, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2560635441623709, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4780977367484985, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.24708913859051898, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4688632265816501, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2560635441623709, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4780977367484985, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.10701006234065982, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3553402191980576, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.10701006234065982, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3553402191980576, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.17631230873436973, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.40948716303664606, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.17631230873436973, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.40948716303664606, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.16436148154531297, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.397352028359245, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1065411343722391, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3734232992811716, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.4126320391097287, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5775573112750654, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.4206365669817144, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.580271336573232, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.31191777012681615, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.47353558787477906, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1813585789583184, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.418713891470244, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.28752161537963966, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.08447773742536654, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2971141035174409, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.08036517486170719, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.35080892963779386, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4257336921268292, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.38564750221750704, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.33113385685815255, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.38179457014405943, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.34753315047563166, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6686626267078195, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2303529811975853, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.601450817823238, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.270465701330031, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6186468607030233, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.30433571457093384, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.23096606881002163, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.18169892215734937, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.10970704443189919, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.11556184719177061, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3962645069468096, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6785332347807157, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.22756030775408279, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5355940887874694, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.40885007148965863, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.20313943660946668, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.49835637707333413, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2196153013796637, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5749676939081495, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.26380148805055614, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.10970704443189919, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4472084730734164, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3538049406567624, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5074236666326171, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3353862189849067, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.14710499415347322, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3568052877265287, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.25318946083294674, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.15865783148776286, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.33433809002301496, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.286272925041448, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4498943788008491, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.20022731236728245, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.42151488713496327, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.011268318581249104, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.10353631565299981, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.009582622912019589, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.10219597724178935, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.09831402774544744, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.01915086268707571, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.117952323965113, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.18846978629906425, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4536070913655126, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1500493128321916, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3450393290642532, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.298553116272535, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2910873658777246, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4167177150134637, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.15865783148776286, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3481222132322815, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.14247195164848236, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.02197369741456696, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.12974998979978772, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.2887138086538547, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6342291345998248, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7013062757071812, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9303769449292738, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.2381658499765768, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8492326635760689, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9063898435384111, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6526460174517784, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8298157168649672, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5309354663044072, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6756014232714684, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4529852871970908, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6941474239078328, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.8522456714074852, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9096914044088521, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.9457416090031758, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9892952933418456, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7912619863720214, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9129058871674676, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.9457416090031758, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9892952933418456, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.37589902061551017, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.42554151277542873, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.20748131961458333, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2716205232346228, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.20748131961458333, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2716205232346228, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.19272923456045185, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.314589204347422, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.20748131961458333, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2716205232346228, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.31383720140423793, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.35896609082765174, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.20748131961458333, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2716205232346228, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.17258341334464164, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2676886314602364, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.17258341334464164, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2676886314602364, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2562402498959597, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3462132320098601, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13020406236745924, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.1949478707854044, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.15751868278140355, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.22016962866538542, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.30613574556266654, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.36162356523761796, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.30613574556266654, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.36162356523761796, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.30613574556266654, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.36162356523761796, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.30613574556266654, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.36162356523761796, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2980986167657195, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3657032294841098, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.18056556996385742, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.29290088416153853, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1277700534498365, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.20846991452438368, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.25985341959039815, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3462132320098601, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.42988105429544615, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7577244658187771, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.5366411241731205, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.825566494253596, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.617939643800199, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8665162960307256, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4360038791211645, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7669087484597642, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.45633698079947865, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7873539040299812, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6153267326643309, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.825440708536967, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4135171000263379, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7050151549073953, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6907573115737006, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9077913232255387, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.6907573115737006, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.9077913232255387, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3345794609803645, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.7523344918083558, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.617939643800199, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8665162960307256, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6099202439984865, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.46997395980026974, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8114935753258365, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.5602926888650678, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8525951197743737, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.46997395980026974, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8114935753258365, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4547722460981925, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.793631811653261, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.617939643800199, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.8665162960307256, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2227227312202058, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.46376525111514705, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.44338575968779337, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.34537865578685034, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6736450219247083, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4165530720734658, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7027805129995731, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4027788021844849, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6872835607174038, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.40245827940445855, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6664090181705107, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5552412314880962, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6976333495952621, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.8331572107884448, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6976333495952621, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.8331572107884448, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6976333495952621, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.8331572107884448, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6976333495952621, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.8331572107884448, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6976333495952621, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.8331572107884448, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.40245827940445855, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6664090181705107, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5478437342181306, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.775208668957614, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5721869364474972, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7849794664517259, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5440766840557734, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7530101164980872, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3623885503140912, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.635707923773145, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5440766840557734, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7530101164980872, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.22447836580911282, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.635962708232662, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.22454359390997047, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6008671717139555, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6537813760269277, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7617489761353242, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3964122180109575, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.584540734626554, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.6537813760269277, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7617489761353242, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.41307323705325416, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5785653391533346, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5248587176134882, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6664855309004869, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5248587176134882, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6664855309004869, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.32797138117025904, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.48645628248697975, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.498704623570665, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6478746389895599, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.498704623570665, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6478746389895599, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.498704623570665, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6478746389895599, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.30654117764398475, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5078250490446609, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.30654117764398475, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5078250490446609, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2280299254440877, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4447177675003817, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5069147001007074, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6481561033107894, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.30783338870673943, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.498704623570665, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6478746389895599, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.498704623570665, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6478746389895599, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4549681528678131, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6164314607426773, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.498704623570665, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6478746389895599, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.45686926996058685, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6147353968946632, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2081154202394501, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4040637852369789, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.062313574266204104, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.35012358768277246, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5816664251371266, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.17729842264695017, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4103582047611184, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.34895836374229405, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4767378358574124, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.4010889714538991, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5642546048162433, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.30145280436636923, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4729753929525169, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21992062963866632, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4070442354164886, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2622716439052442, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.42384915893461766, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.35210829264331733, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5239651686730163, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.24831757596380594, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.42241157904531507, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2550784982476315, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.41390693736043466, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38732841080078323, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3556696449699231, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5043507390160538, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2830789070123405, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4900779362555344, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.30690336937373786, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.46380735910652676, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.23632009599741205, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.45434799944761456, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.19464521962073492, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38584042605633057, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.35548377438423956, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5150536106864393, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.35548377438423956, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5150536106864393, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.31410396987414585, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.35098096867859657, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38561859819475125, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8958039312312598, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9382091007325469, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6433799261824519, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.81037697367602, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5403356450597102, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7639130574395125, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5815699184831468, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8158797976578578, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.7216597075217096, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8647649160356543, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.7637483416234716, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8894308321293988, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8097013849965253, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8896806148658662, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8097013849965253, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8896806148658662, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6161420984415483, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6945809713247855, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.833078701050083, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9482515348146272, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4500531895417844, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43027065541050147, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4933292241270431, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5225247297523148, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.23487811400114963, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4062284746604391, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3763743474188506, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4017565065239436, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5135063580594283, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5263652476607005, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4933292241270431, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.511824430191619, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5805399561362194, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4810464260105228, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.15764980576646254, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5717865334172536, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.15764980576646254, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5717865334172536, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.21510618470971102, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.41380245501613677, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3489214645008508, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43287961433058714, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43081631154211786, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.49539605131242165, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44728880966754114, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.47426640493104016, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4602272932792115, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3489214645008508, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4519496200669607, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.49539605131242165, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44728880966754114, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.49539605131242165, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.44728880966754114, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3917196589390866, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.555059558533586, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4825434542324755, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.5617848264135781, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5570886750436929, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5212982931053122, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.35319015092357736, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5822934956325967, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.35319015092357736, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5822934956325967, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5095895501997145, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3532802306487636, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5839265501529569, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.49961369350177665, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6351045115684573, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5064127215831256, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6516332048338376, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5064127215831256, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6608872773156567, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5064127215831256, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6608872773156567, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.35319015092357736, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5822934956325967, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5273318485276001, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3532802306487636, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5839265501529569, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.49885432872486163, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6436097366017006, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.347738559973399, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5870908284609656, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5064127215831256, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6516332048338376, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5212982931053122, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5212982931053122, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3732103775315803, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.599753778627387, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4647137781420131, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5064127215831256, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6516332048338376, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3855522725905196, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.587260566914102, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4426623526629488, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6368371029698285, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3666340989897011, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5782960278998768, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.32892676518285585, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5800761309604682, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.46550355389682435, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.646730632916617, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.35138749399652214, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5704306601285767, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4592978565863154, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3299895472527792, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.505943186361187, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3299895472527792, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.505943186361187, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.29456425448249246, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5691358329649412, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.29456425448249246, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5597065389350384, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.17112018824070996, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.45537231333074557, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.46550355389682435, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.646730632916617, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.17317111195623838, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.49608097529808043, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.15083364266523736, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4714472446464193, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.25376192011637994, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.47199515498282607, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2679646241939333, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5416663840402111, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3571029859832319, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5866468420684132, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.26349889713915725, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.12514328743841557, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.34961836061490087, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.19650854773882592, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5134302167765095, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.518761522736185, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5205634208063233, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.518761522736185, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5287371836061487, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.518761522736185, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.518761522736185, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5199744506588604, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5199744506588604, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4397936463531347, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5197498882205425, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5199744506588604, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.39814417587130846, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6510906999464993, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.19650854773882592, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5134302167765095, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.19650854773882592, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5134302167765095, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.1739898487873076, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5216901258730671, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.18960267898639677, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5147057623329436, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5199744506588604, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.48994178177127756, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4916235564562672, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5106109398471469, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7688046995197549, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.44778459441351737, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7043336945393497, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.32214112487007024, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7794716829174484, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5564992960428438, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5129586382458503, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7857394056399366, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.44778459441351737, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7043336945393497, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5129586382458503, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7857394056399366, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.44778459441351737, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7043336945393497, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.44778459441351737, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7043336945393497, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.48222455960294414, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7511716303980656, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2078053264420889, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5406521594311308, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.19288600440785333, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.39234287919326716, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5106109398471469, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7688046995197549, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.6725157402359803, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.8704716256581455, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3494188591554153, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7072510223788713, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4544489097785626, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.8155088724539601, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.27693481162988715, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6775019273554157, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3012697212106696, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6712254595250785, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.39693478727333953, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4824766987096576, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7665355959167616, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6158161554766717, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8568982835533138, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6535194995338728, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8909391457425937, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6535194995338728, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8909391457425937, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6535194995338728, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8909391457425937, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6535194995338728, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8909391457425937, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6535194995338728, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8909391457425937, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6535194995338728, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8909391457425937, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.6158161554766717, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8568982835533138, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.4062749424452353, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7717578180410056, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5088645484558708, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.8116199676115453, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.9390825256401198, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.4373266725468241, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.7265900332348232, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6810920170253699, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8151678595510182, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8873630455888943, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8571061116877262, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.906026511295714, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8151678595510182, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8873630455888943, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5386933265263314, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6707532211471023, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5852187596735429, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7147018027438421, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.7298378378464025, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8542310686470678, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5852187596735429, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7147018027438421, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6317498622799441, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8119634168566612, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6317498622799441, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8119634168566612, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5852187596735429, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7147018027438421, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.39569555015790975, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.654677791684296, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5846059222883585, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.7483293841345244, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8146526693270999, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.8151678595510182, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8873630455888943, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.7483293841345244, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8146526693270999, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.11392322187442314, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4512595975949005, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6268498243626915, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5852187596735429, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7147018027438421, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.39882161697649804, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5852187596735429, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7147018027438421, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.31684822717918226, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4984008175596484, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.31684822717918226, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.41779931059703573, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.31684822717918226, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4715336632468998, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.01834337391695103, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3682241310101735, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5450474312451057, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1540231640374204, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.36182698586213136, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3682241310101735, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5606184355158915, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.30717471678915614, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4836163769308175, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.30717471678915614, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4836163769308175, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2765950320972588, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4432072463778114, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.36197244208226037, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3081498800129959, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3682241310101735, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5450474312451057, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3682241310101735, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5450474312451057, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20248027846537173, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.435318130545113, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3682241310101735, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5450474312451057, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.35620708925421163, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5293559991315759, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.32620243905074275, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4654796791877148, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.17415784669090767, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3586870164339305, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3682241310101735, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5606184355158915, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.25590356077469273, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4786634069414725, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.41469320341466864, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2371332024655201, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4712410964015287, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3762184183716275, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.24622924391353238, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.483120102899027, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3733886407390251, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.38216426442206797, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.41469320341466864, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.41469320341466864, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1447953615777742, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3672186527241423, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5017688442812349, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3398181362504403, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.25590356077469273, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4786634069414725, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5017688442812349, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.18216041731535018, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4452929993740753, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.15763647528667518, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.44489192252868437, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.35987632082503146, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.47242552761762285, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.44449614932648224, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.33514014117550306, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3832378601967276, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1635655187775842, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.43041151847878933, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2833653799320801, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.17493298656673703, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4597805060995162, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.15911783110981517, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.43917006704544925, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3162730677141066, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1446920532195634, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.390638522705562, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.14153945350617025, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3789032029729825, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.29913853007133406, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1892240568795935, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.413299350315557, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.016642483540319063, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16012807922240752, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3670896699555711, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16279348731624776, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3909559744576112, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1523624986106406, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.48503882116076147, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3264336472812388, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.14054613281857953, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4001732894164143, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.17311878877656692, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3787369939968744, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2369690015211867, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.315195724666321, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.5709867732881334, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.898461683304813, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.5009303657723724, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7151387779856716, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6721494116745023, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.82229642880017, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.435949382480739, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7459582755815383, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.47207580389427084, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8498299925939343, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.25970649707456084, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.679667737737626, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.33488655580657256, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7293017619227443, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3079852790634304, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.6441930748012042, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.37916211129533023, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.695594076304475, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.22848056414159593, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.46412553170787146, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.32716086252780224, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3963747719907255, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.37192780061868996, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.6892896281611525, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.43781869404573154, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7710721800807774, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6289868866690355, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.818026118975927, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6289868866690355, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.818026118975927, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.4071359919668265, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.769719633686151, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2111187176080899, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5500149009411459, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.25292225602558815, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3639412530979476, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.6558757084256063, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5294365116477578, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4115919883568686, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4082143130164669, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5109063149611607, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4572935209207519, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4572935209207519, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4768283301747848, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5067583406451532, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5067583406451532, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4572935209207519, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5424577953561173, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.48832236072170526, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.45365562700803175, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5067583406451532, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4017552060255782, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4095191931337695, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4533179790364423, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.45365562700803175, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4039245319097338, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4477905900494404, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.47331152665045856, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.8148863881905419, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.20352458275127414, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6347163227772256, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.37738482597205875, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.7950074174417372, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.14529647371369342, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6260669205212257, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2411108351008944, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6937177458584591, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2115210387013347, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.667519467729798, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.32685141385924577, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.70370764261192, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.4301256869954793, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.7706340593676131, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2930010353512543, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.7440537717085414, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.24659038451613516, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6742202736673089, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23713320246552005, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6907833610938203, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2256490809237466, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5866569481329091, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23633399735350868, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6998524249051279, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1475954394771886, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6528001650752809, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4957546540557718, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.24434615132870352, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2997691103544319, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.718671272125112, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5852108991184741, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.44374537633106365, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1150950994149918, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.561451772736876, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3449754050963302, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5521970778133709, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20304086026162935, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.42692494747660203, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20304086026162935, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.42692494747660203, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.311238976401943, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2175445226496326, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4621999154927885, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20853111243606828, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4435193094920918, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2175445226496326, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4621999154927885, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.14253167772862407, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3600387580548723, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.14253167772862407, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3600387580548723, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20623370300159788, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4218885357875893, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.15987105932093174, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4326511028690849, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.15077961452172084, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3926830608744669, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2175445226496326, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4621999154927885, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.22408126327351324, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4635198584730167, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.19416717060109628, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4004538610234101, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.15358735839457807, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3955148125267572, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20853111243606828, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4435193094920918, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.22872196013470597, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5039380180064673, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.22562504461821242, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.31412494195165025, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.7973454774914206, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7689312469180218, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4831233610237384, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6532633714920698, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4867643691804454, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.64607619022599, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2814017327307182, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.496330576799077, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.794834366062997, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7747058711066555, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.13421952443691573, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1672261435520376, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21470005952317833, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3190887215348668, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.27232975940069765, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2618225775948002, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3154042850363793, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.6941268297866866, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.7232925116612475, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.28688236146427454, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.30588462336040045, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.24388575959910294, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.24388575959910294, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.24123834935482885, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.30588462336040045, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1715463764333805, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.17571089085620334, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.22262500195341844, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1887792103487876, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2176061023319429, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.29799812108040613, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2920370029693632, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4216533376172454, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4039571839139068, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4182495832421204, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.41184258626249504, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.19230188007838597, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.24907067260370286, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.24645013697131232, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2775164476006572, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.23587293236782791, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22109333005198922, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.165099903439123, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.37585464732579915, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.36761798002928614, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.028350234434630903, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3231493408508545, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3101339436487065, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.5951888718948775, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.519769605051086, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.1850334785266634, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.636855658754492, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.598421012757662, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.636855658754492, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.598421012757662, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.42690137964167635, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.44383714733988183, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.21712457973411817, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.31211920341047517, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.29799410917087965, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.49831162551286645, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.37054866173134826, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.1988908085691084, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3279525547808158, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.06999105251612557, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.15760436972905018, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4578730121271583, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4763409764863904, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3210886805532631, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.35007227309343614, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3324024618080297, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5526778778205866, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7267402732246275, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4779289657345161, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6131584716544094, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.503423182754679, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7185797049975355, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.503423182754679, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.700643793254282, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3685289119518548, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5839727029732353, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.32594974619751477, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5361018684083835, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3190887215348668, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4863428828999999, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.503423182754679, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.700643793254282, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.503423182754679, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.700643793254282, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.35345481163747966, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.600086974472641, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3626305461419687, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.593978460413095, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.36227557436010244, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5653237160901986, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5526778778205866, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7267402732246275, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3626305461419687, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5835071609276217, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3685289119518548, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5839727029732353, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.07120149575853292, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.3048128700747796, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.503423182754679, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.700643793254282, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2147607499133801, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5078156364964329, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.33403925633579773, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5319774706581363, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3626305461419687, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6179355732290436, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.4721001028256397, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7096678127067526, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.4336560555138203, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8096970872393391, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.7016116562610203, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.9349183533264898, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.6298777848185599, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8784032559879915, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5642137945405272, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8202028423242187, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5642137945405272, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8202028423242187, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.6298777848185599, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8784032559879915, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2999242985334114, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6283146443097338, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2999242985334114, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6283146443097338, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5214131582612217, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7585614280322228, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5464711341087805, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7864029396663078, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.47022156411316, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7153092713985418, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5582220191559627, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8140951454638551, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5582220191559627, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8140951454638551, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5649285678830409, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8161130615280334, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5577288803545524, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7974046579591895, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5577288803545524, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7974046579591895, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5988044702245784, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7681690981335013, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3713830979377925, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5751167640035276, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.8407226006325472, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.13072010980679707, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3105434451119841, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.11967758950157248, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2800855102887508, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.16417215667010873, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.36947928854089845, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.12743800102943376, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2780344256680002, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2935328201198795, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.43434504242447536, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.10403896883688996, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.311533423157872, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.285255290869053, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.40782828620425265, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.19629722764755747, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.320182335345892, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.19629722764755747, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.320182335345892, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2782546338934227, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1260969365429506, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2687407910300558, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.16458036334354648, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.19568336427344607, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3723430986912162, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.14724619050922358, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2839286654333982, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.27486902500051297, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2283070457730447, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3919468075768785, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.167045425494737, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.34131323228943095, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.13382613080002836, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.30519034852833676, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.14694567648694842, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.08541575654695113, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.21856618331280497, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.37453249276032596, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13471766853689124, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5276176357172093, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.15875722180934987, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5368911830688495, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13817790393734294, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5050266837640857, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13566979610140004, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4650537985480846, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.39489495287005755, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2320305803246989, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5875457251146547, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3678659779998934, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3678659779998934, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.39584294700165096, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3593318822560319, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3064223067887308, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.16564565321939206, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4536039871760293, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2476165058078653, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5724037747915761, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.29456425448249246, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.603721366747684, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.391672963267396, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.12409597120849801, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.46250911995239685, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.38466593078622596, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4113262406569788, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.12259149958656422, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4797495741142639, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3199526749905591, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.46625097311775787, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43437903147819623, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2970991781513299, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6304107643405119, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.14527620275146488, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3233041457926855, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.37447417181493453, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6453688418182368, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.23749937482512903, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5186241423639549, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2293648308471323, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4184099073786108, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.12982679446701692, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3598851490125971, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.12982679446701692, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3598851490125971, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2583858837827738, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4449030747393809, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15184543565627642, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3316482535817426, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15034744819187046, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3379957017327007, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.6007525446699544, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7052132029482998, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.491888791452497, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6514476893155858, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4640531756865941, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6384698340031734, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15016650105868437, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.38273138700440895, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.26822974402116034, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5226016850517986, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.13064622864882905, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.29841237721609765, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.19685847267728884, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.12913533075470382, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3699122403233082, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4012179884342934, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1751062735415077, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.48664097065107126, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1751062735415077, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.48664097065107126, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1472462377094902, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4296561364586918, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.40354716807491975, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5496664962676806, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2557914670300308, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.49203564396422345, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.37595662994657586, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5278838809443244, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3764925637801421, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.598648554589699, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3764925637801421, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.598648554589699, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2460137257692754, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5651300593558061, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4252443015971012, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4389754417832011, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.21413989011971157, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5141525252714602, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5162619434676526, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.7117190161792883, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3964543810570382, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.1927369155899176, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5652312627454582, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.22878684333741806, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5910527597265157, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.39376010611714934, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.11165817735905989, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.459384056941606, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.61445237198357, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.4111336169005197, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.654151133443915, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3911104256806521, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.7162899586182385, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3044269773076113, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5765179983591493, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.17770114738246548, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5263352658491535, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.4447630178181816, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5830457051905695, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3481790920114991, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5546274930344433, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5129484309843931, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6268186944844665, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3977135991359948, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12991916506579942, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.442586106514705, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3152093058791381, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5618098981717927, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.35630548449868954, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6285749485464279, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16618655166630525, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4875519643561779, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.25567957494892185, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4986688668174522, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2278350766012413, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4991401820950425, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.27241282355631563, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.44521047328947694, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.043407736034766595, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.26016211605713957, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.4390960897971484, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6485099247319526, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.15511550090520096, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4014314464220935, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2943579102986884, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1890425467840326, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49920100551781216, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.13566979610140004, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.38699631006193164, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.1434533437144611, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4325933876557919, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3182117086067523, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4064888217189732, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.21800193956058223, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4699679052795741, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.13308442527111022, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4188741469277716, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.23114663823833642, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4894179053435348, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.16299446731288944, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.32080086594496104, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.22325877055095214, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4093357710583615, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11856660123276004, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.27382044275399503, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.06534878510818803, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.28228674987841224, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.0117896747628835, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.15448759309616733, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.42469356957489807, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.40517879381475214, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.38553652887288764, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.02629161215521893, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2325340467951448, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.21223633441554032, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.43890529347423884, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.314919081947931, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.028206246615527588, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3621071214396606, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.30702571862234085, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5270937279585078, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.37027304017004864, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.649647473010403, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.37027304017004864, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.649647473010403, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.37027304017004864, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.649647473010403, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5545363548814882, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2810335395782485, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5956686674268991, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.37027304017004864, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.649647473010403, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.32282138800401855, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5705123444441751, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.28615556452106294, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.46306995992822714, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2291421308389693, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4574939601395284, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2850782270836371, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.48913589010736547, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3208090524027114, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2520126751139802, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4174826402445743, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.40792735592133966, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2520126751139802, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4174826402445743, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3172479410570454, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3172479410570454, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2255009728657898, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2079988964349653, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.19034686962671285, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.28615556452106294, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4803502934592869, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2520126751139802, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4174826402445743, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.40784251617180445, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.28615556452106294, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4763638923491097, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.24248545140243574, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.43733358879787526, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.41303058168387535, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2079988964349653, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4508926953372328, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2898497051727735, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4696277526071703, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.4010889714538991, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5073411865094402, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.19428231170553664, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4516757290152384, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2250265947708922, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.41994943513577565, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.36938092578764037, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.513005525044022, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.346982495809083, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2286960004658595, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4746698507981419, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.07439001436205736, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.17201012432847057, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1196268811190815, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.13166139176601574, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1629057627580272, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.36748173214650165, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5111850166718516, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.24701991296369977, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4634617667206513, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.5696705282375883, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.6515641575069311, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.318248515465579, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5345496330406173, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.250737833894674, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.42608188471611363, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.29189371587790414, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.004111318884175239, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.2259609947599236, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3263040636562357, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5971070986250356, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8874294965619517, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.7511573912724299, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.9453473543978153, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.5561195823338172, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5362935676066722, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.5803515898273521, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5422220468910552, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4204739940979302, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5173824078732066, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4177866849157374, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5243375045345786, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.4593860924266348, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.5045746404501606, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.328872375046221, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.39142733167976973, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3450219162509876, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3993348853061597, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.42670493571995677, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.42238844134044595, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.42670493571995677, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.42238844134044595, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.30978068501889056, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.28295274449167956, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.29222904325820687, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2723003396696643, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.29222904325820687, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2723003396696643, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3567464687150701, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3651755892066728, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2548454457146799, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2714025628458789, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.33498389276277546, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3296536654279081, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2368693821608258, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.320909989176825, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3942831699210502, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.47635688895853756, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3031148374457066, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.28706898608824516, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.3223833286593516, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.39475158383309167, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.46146548771819573, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.4019452398054806, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.33438299066966715, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5409759573191787, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.37854068916316835, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5743796566387722, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.37854068916316835, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5768306472334509, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.32134504358579785, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5076725973953424, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.30759515980677804, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4988668235835214, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.29300728994404895, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4620516485185446, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2562150245540302, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.47046477830594896, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3545085634416642, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5387990402562496, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3545085634416642, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5387990402562496, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.27182849679730653, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5497265770945076, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.12001885809269497, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4122127192166065, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0956774578033165, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.2538064061386275, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4544505188404086, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6033006987520517, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3509258729305825, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5379703355059909, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3509258729305825, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5379703355059909, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.38936263771250235, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5443518219250745, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2767438561951455, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.45932437705906165, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.38936263771250235, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5468468646357602, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.28555753499459907, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3416445560351976, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4049402235047407, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5871644977560334, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.45506803308128024, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6477506541284608, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.592313615748771, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7382416555842614, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.592313615748771, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7568286018427376, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7389181446831377, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7389181446831377, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4226108216696222, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6493613256786125, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4226108216696222, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6331414171574684, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4226108216696222, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6331414171574684, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4226108216696222, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6331414171574684, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.602867050301643, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7367363357155757, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.5521710658453207, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.7317828775912516, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4018202851356865, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6003256951549871, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.580451128369423, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7542976177437886, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4018202851356865, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6003256951549871, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.526357446896968, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5582486914071635, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6678493404097802, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5582486914071635, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6678493404097802, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4018202851356865, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6003256951549871, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.8406763479345174, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.8871517153603867, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.8406763479345174, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.8871517153603867, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.6666823117022298, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7571125338649978, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.6977240390484037, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.818984467219358, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.010191247541026162, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5406438522344627, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6520694800788391, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4018202851356865, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6003256951549871, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3864572432237816, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5849342936087653, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.6977240390484037, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.818984467219358, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.5793367580502561, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.7675449146326079, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.48470790736249264, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6505709783584183, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.7019499719108448, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.8450280883390384, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.7397087417978795, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.8865031414920428, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.37717457428685847, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5554130492458337, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.31598923484911084, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.18953162992336403, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.45876745950873354, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2383770504614087, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.466645869611307, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.25567957494892185, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.456155589788991, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.20422838465921236, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3821382671218279, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.18207052811092134, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4504432021668592, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.209100828813675, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4538036435159857, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.209100828813675, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4538036435159857, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.14291173574075158, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.45184360988354105, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.22059202034059508, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5084868416945086, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.10087588344601466, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2599542517888651, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.49098929416640624, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3099627272480552, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5091964648046775, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.34419514726440925, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2128497674847141, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.438591227628555, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.23832340744793254, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.43652543518564646, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2066736214472914, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4458626950255153, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.16170596160446446, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.27743662258385243, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21081851067789198, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4042801758173556, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.7629273292796576, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8510385544954956, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8725129388059689, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9495292423959529, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8725129388059689, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.90941532255964, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8725129388059689, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9495292423959529, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6425503166524515, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8078891929749037, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6425503166524515, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8078891929749037, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.7181417752544185, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8029162546307379, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.7181417752544185, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8029162546307379, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6425503166524515, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8078891929749037, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5970228993860437, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7623592429154771, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5970228993860437, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7623592429154771, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.7629273292796576, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8510385544954956, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6425503166524515, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8078891929749037, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6888074582865503, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8055061207769505, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8725129388059689, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9495292423959529, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.8725129388059689, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.9495292423959529, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5970228993860437, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7623592429154771, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6978429290017016, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7717858931341154, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.49349163706233623, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.694445271037971, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3037643089519314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5183662698462751, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.18376711147874328, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3981272326046884, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.340960560695735, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5217663812589132, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.29898984447859595, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.535975072921985, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.18189587992135597, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43964080400724653, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2147607499133801, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3976144917079093, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2745762486209681, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43603011963088695, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2745762486209681, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.43603011963088695, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3941175366175992, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5506555496793699, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.36067814893280986, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5071206995409688, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.1896550847075289, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4310936955011834, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.6495308560002527, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.7114963534919011, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.40589517638127065, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6149515961727072, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3339087646492816, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5995623358499859, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4122974402951816, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6170911690364487, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.32672940262046324, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5803377043012041, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3785572829193946, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.2643854378698732, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4066689638009577, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5267604642487788, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.8253498772794055, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8529564805429163, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.7944837206494969, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8784531740275225, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.7944837206494969, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8784531740275225, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6941268297866866, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7679844670813416, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.8253498772794055, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8529564805429163, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.7944837206494969, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8784531740275225, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.7072172847953276, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7914639887327892, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.7072172847953276, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7914639887327892, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.7944837206494969, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.8784531740275225, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.175538121835486, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.44197441533246407, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.5828833474188783, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.7908226509294533, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.38694317759010316, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5953878513137957, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2620499195763038, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.48937240022909234, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.22128776529156546, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4999323991212311, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4272870063962341, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6271734609265041, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.26332019392396333, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5893220054460814, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.23887527917609022, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5924993690004501, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.5394044743801475, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.7201188407944494, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.5394044743801475, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.7201188407944494, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2745762486209681, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5730023382770898, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2961516536011624, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5798430117187255, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.14101576878340707, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.35998495164287625, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4161791450287817, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6046852394200818, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.28089241320678904, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5475272889495614, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3070898761263382, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5791648909423264, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.31600229153053044, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5374439094267343, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.21690365808279138, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5019141380515013, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.009494440414752564, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.27733310601709266, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4703077247331959, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.7203673717155472, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5040673596100225, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6469962279041276, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.22816849039973935, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.49849908693271183, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5106109398471469, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6635467152827634, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.325909498033977, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5501364764829885, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.7498810286408993, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7726337964681356, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4369942407063455, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6009573115008555, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3009687072297843, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5341810386314462, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3009687072297843, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.533217285012153, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3009687072297843, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.533217285012153, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3140382293917749, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5631437828635808, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.22816849039973935, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.49849908693271183, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3140382293917749, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5631437828635808, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.7498810286408993, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7726337964681356, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.7498810286408993, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7726337964681356, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.7498810286408993, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7726337964681356, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4167743222652789, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4167743222652789, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.8318180062062374, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.8641903026295611, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4806216298219478, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6311658995293531, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.7186969683828063, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.8143071707828088, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.395494817172382, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.48210216762305635, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5029543425204815, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.22543108408457457, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5721164465661742, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4884391791679525, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7050595167501005, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.15495096883986592, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.45421263258392414, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5138104164912963, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5123350305765596, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7719555466081361, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5123350305765596, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.7719555466081361, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.42099734580654347, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4355615888320689, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3548263685679835, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.24518299917312847, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5623282316325473, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.346133586314057, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6386405249336979, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4773779562574767, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.22119423000583918, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5855963149167847, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2009685362442462, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5922962229661707, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.19514193023219964, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5096213500210006, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.2772639581765057, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6585810035136251, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.16111212240349498, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5162765195160328, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.23109536367862135, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5693079918450474, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5052082359105701, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.17991078645928837, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5159811845433955, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35504200505176187, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5693079918450474, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35504200505176187, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5693079918450474, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1794560313432444, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5236301264596329, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1794560313432444, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5236301264596329, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.17991078645928837, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5159811845433955, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.45963072970927465, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.17991078645928837, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5159811845433955, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.2423268307137331, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1794560313432444, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5236301264596329, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35504200505176187, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5693079918450474, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.45963072970927465, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35504200505176187, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5693079918450474, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5052082359105701, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.17991078645928837, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5159811845433955, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4492950042617377, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4608738248525917, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4252891537802403, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6269243845872724, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.49831162551286645, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6906494695103921, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7887116805325072, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6325987025085013, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7966336957924106, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6325987025085013, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7966336957924106, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6325987025085013, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7966336957924106, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5694299147290928, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7161974280320248, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4601221424835303, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.670463478293434, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.29042767355630905, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5945109731611824, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.49831162551286645, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6906247423308508, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.788686710424071, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5694299147290928, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7161974280320248, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2624310277292268, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6025429011085721, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6486932415130529, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7887116805325072, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7490853969372642, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.7869453805471358, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.4970449067437269, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5549084692917513, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.47136688868251947, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.532838700147956, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.6158362062506663, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.667219143613408, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.39057277619092257, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3934016321632531, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.43937095446369234, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.46181721677136944, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.47136688868251947, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4875567860488344, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.47136688868251947, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4875567860488344, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3246935344198473, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4118595729651108, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.3754749996604944, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4281102173188986, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.29518557226324804, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4165838256619938, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7490853969372642, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.8062091543413888, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.44055594594452946, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5608379078395163, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.4462203715133425, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5604772871598175, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7490853969372642, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.8062091543413888, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7490853969372642, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.8062091543413888, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.5196976495259397, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.5405459272129465, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.5054091115759235, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.6683122485502007, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7378351342269067, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.7822638455166255, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.46463179926223586, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6658302112115018, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.30934066139296057, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.45568578346907496, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2982935802892967, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6025685350602339, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4546828804875388, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5363479231731832, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3917244017992322, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6342898219503306, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.42406493223220554, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6515479761083638, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3460178707517162, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4777182579951077, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.22004975188435827, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3580799708721354, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.22004975188435827, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3580799708721354, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2331039707351165, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4183718943912669, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.27131642727612953, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6108644122399178, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2028609724458554, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3641531893505486, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4772349067014227, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6979552346144655, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.32144812240790727, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5957892991708469, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4041996150245149, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5081120456623677, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.33710215617303335, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.49211592362146866, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2206635048675199, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3982161812429023, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.4220575161811247, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.567941545813889, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.2411874285895162, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.7000942696222402, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.7771546905544982, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.32375968335328725, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4184987692475953, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.26583802173257376, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5022872142270257, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2928787572874777, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.46379385574395665, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.5728145662417075, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.7040427611843448, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.6169034543248991, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.6942951271142352, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.6054657750562688, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.7275033089428229, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.41103851467561064, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5051296804607229, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2989834108541526, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3436978703286461, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2989834108541526, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3436978703286461, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4290255653710564, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.559834009444831, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3910016226314522, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5825568684453398, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16917954480308722, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.24861820310138238, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.45359393336810816, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.6211966673115089, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.24876675536871823, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5735144784700121, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3042060837668054, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5646760672180815, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.05909067563124427, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.29914758135590824, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.4458819273326583, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.63263087218045, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.19378256970654398, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.37585899878773465, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.3626305461419687, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5172467980765818, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.33573064840973227, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.6896084087753593, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3294509143325626, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5502318837669161, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2589451141492935, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.522870128470283, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.47843809609003357, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.6639502807777604, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3975205618000645, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7019684122171391, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.4093632136736518, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7444177757069163, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3680806213583401, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7106717690083967, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.23731319709526777, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.56616019140197, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.23731319709526777, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.56616019140197, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.20383958833634852, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.12854865542367813, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.29041306954676516, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11865659854763386, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.29336156127730795, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6879419393521872, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9251514068996235, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6248651455191909, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8644374396148615, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.49723587033674593, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.7738363285778612, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6508430035585083, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.8046848309301634, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.6879419393521872, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.9251514068996235, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11930191477839873, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.45709744918566686, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.14072301632107687, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4881069342294986, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6102624546684577, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7455382911279661, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5129914365244811, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6719058099803666, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5129914365244811, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6719058099803666, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5119999466045957, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6745099802934275, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.49494318987722147, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6525478644418932, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6102624546684577, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7455382911279661, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6102624546684577, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7455382911279661, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.49494318987722147, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6525478644418932, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.49494318987722147, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6525478644418932, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3961867597457338, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5900232242858499, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.28756999622055585, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.562349006774183, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4717991357336539, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6368175528583246, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6102624546684577, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7455382911279661, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6102624546684577, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7455382911279661, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.6584518248758039, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.78947510218162, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5936781016890555, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.726845452474233, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5129914365244811, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6719058099803666, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3911295456386654, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5800089719996314, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.43762500187316666, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6229933226678195, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3961867597457338, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5900232242858499, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.18558816000270506, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5082547077193023, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.25104615680952314, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5386684376521024, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23592677325793138, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.47227033885649483, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.22872196013470597, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4750367449212949, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.14239015212277228, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5183430108833335, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.12607162121844206, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4374864219311677, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.42219590199110324, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.40897782965894874, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.40897782965894874, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.20185773580773803, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.466274292216381, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2801260476496127, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4918406628443769, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.51375768621103, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.24447640553662225, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5297512650421087, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2698809072033866, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5827120908586206, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1180263199418922, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.48888367066057226, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.22908101428437017, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5037331050598365, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.25100150428977114, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5078973712791223, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.34872397046357567, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3077112060330384, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.18555515022041807, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5078671061112421, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.4158130624959958, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5675993368017754, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.034234536820051814, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3041065177261626, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5406223711214764, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.16020720994064927, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4494779997964713, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.15736937921428037, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4141688451038981, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.169398499987232, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4808428623530613, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.35573896339264094, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.43373844074577966, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3830947997613699, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3830947997613699, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.44383351844821595, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5658578761464655, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.2612246288823396, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.46227338852099076, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.36482717719811386, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6036552405597372, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.3040052734530821, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5563245065214154, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.47581040383390794, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6192989319465453, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.40025074540692385, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5277651665395992, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.31823566221963034, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5315680645260001, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.31823566221963034, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5315680645260001, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.24014973510773413, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4758492311424834, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.25134915147946046, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4837504342576208, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.333388748608888, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.38969673850929676, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.391080327529236, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6466158388142541, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4464617303464354, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6719518780034501, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2291421308389693, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5523264448305787, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.5718458251358622, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7377760376723715, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2291421308389693, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5523264448305787, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4290255653710564, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6542302592826403, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.5438653754915956, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7302649909837065, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.5438653754915956, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7302649909837065, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.5438653754915956, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7302649909837065, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.48381346304516887, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5124459840529199, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.18188243375551016, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.6612116051683129, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7760591039106626, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.5438653754915956, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.7302649909837065, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3060368950930091, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4831305031819278, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.32178169209299745, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4853985554034008, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.42601467364417966, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6715816583904739, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2615311775021803, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6168046788492375, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5152958249888121, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5435363281207461, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3964023716675737, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3718976854103865, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3063889665164676, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3060606492644399, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4392283615599068, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.44496960530746443, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.42262353460370816, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.39118612205954695, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.25609516769327906, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.281538474327709, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2875583820017638, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3019039432257823, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.47901455811287486, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.42929076670455985, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3226647471194494, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3327820939566751, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.32214112487007024, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.33046168816283755, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.251417351368381, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.28946399423161434, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.4546697236991713, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4460520024887841, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2566290206865396, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.28445804097491273, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3179303998422513, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3849979751929991, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.15911783110981517, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.164451438302013, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1931328231343031, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.5426552583629827, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.5035808316842799, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3968302282220472, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3941633568645063, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.45928067977039955, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.40650204723524674, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.3702794920873997, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3917352141397069, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.47901455811287486, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.4956337510935212, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.21305956475594143, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4395285386678049, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.5439405004075281, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2348836443827469, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3379049312559404, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.042135153740247816, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2348836443827469, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3379049312559404, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1423071532720465, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24796510465152288, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1714049169603588, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22748922852371126, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.5216690820512558, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.6663479473341912, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.5216690820512558, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.6663479473341912, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3461876785833229, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4375133561627813, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2674342279940095, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.33258450965972425, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.451818443605239, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.25270455578796175, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.29757523241220163, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3292010361291119, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4311130504810004, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.18239350853723665, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2213631608633465, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23477883426250248, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3032766573571171, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.5102002548573253, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.5481850559415788, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.17148143565512755, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.26771555499834426, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1832567180568652, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.27347298550058124, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1709686260975486, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22586346179982364, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4093184131170722, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6844082266550039, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4093184131170722, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6844082266550039, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4093184131170722, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6844082266550039, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.39022736644855677, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6827449888069321, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.39022736644855677, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6827449888069321, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.43037677381220035, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6909233597423888, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.39022736644855677, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6827449888069321, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4884391791679525, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.706162766244523, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4093184131170722, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6844082266550039, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.33094680953828387, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5082966623697348, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5194247346787363, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7440660671846263, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4696150968541076, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.22656720908801994, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.631245192197625, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.18992435055904786, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5008843990379334, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5116579033814616, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21535397121201075, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5925940104599001, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.29108736587772466, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6461260377075316, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24268235789067255, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6128667394032248, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.33249685664456036, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.637090236976522, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.33249685664456036, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.637090236976522, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.43083309595945174, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6660840730280997, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.5051836989392832, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7047307770140406, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.16616411230693814, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.45262530701514303, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.30205846864298064, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6431625523291072, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.30147856626075187, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6165177250649315, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.28685780777240977, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5505861134074188, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.28630708814903527, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5730343144709868, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2026478723972883, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.542836211081738, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.34657561901567957, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3185890261553478, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.17679588126795498, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5270697005877061, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2882258334128601, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4424981883607872, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2882258334128601, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4424981883607872, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2882258334128601, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4424981883607872, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2882258334128601, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4458584061535501, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.16973628531343277, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.33812107130297947, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.173167034608353, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.35485513246564027, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2434623104231637, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44265412961841627, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.5245322414712715, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5814854113930948, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.5245322414712715, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5814854113930948, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3489214645008508, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44435817070504785, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.42657068031281004, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5676570548521612, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.34961722361745307, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5137611857380029, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3654749251620566, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4608305787020976, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3131480143934657, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.30536941697562214, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.463676504477036, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.326982251281397, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.32823975228899477, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.27593241702034227, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44400051895240894, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.30536941697562214, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4724348641780438, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2412588049712986, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4536639990242445, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.21281701380712922, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5028404616749624, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.15295559337528836, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5217846954711376, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.20036529832558245, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4411095116549528, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.23804003814061675, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5256271784759383, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3957831377655053, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1447953615777742, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.42451849651929324, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.37257484093951504, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5542570357348661, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14153945350617025, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4269729411131609, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14153945350617025, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4269729411131609, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.20472658408422542, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.48478811641801983, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14167966116048497, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.40914138828349356, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.10344868765524623, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2279301587823655, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.20664181816537017, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5143883509283346, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1143433820088083, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.35470781080011465, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2676032275663791, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5128827077378436, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13737279171076758, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.41264185474099047, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.2042128370387497, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4468235873099241, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.22354445094404488, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.45921484835729326, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.18082678642487518, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.27195592687669795, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.5350448626134884, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4323312773819961, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5997371746139766, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.49935841995256924, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7295897846667867, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.6510651028008023, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7734123056546561, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3606966647394869, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.571396396984912, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.46227871261821646, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6461151022797409, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.34592991251442967, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5677282056948096, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.427700699409628, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6058578812402458, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.22526021557690604, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.48234602030711826, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.22526021557690604, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.48234602030711826, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.6275541561404893, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7316294988783622, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3954642331526574, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5607387096042565, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.344268011447701, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5316720524252836, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3943890898713652, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5760332856685048, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.22288552654078472, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.48701612914140385, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4070190836305988, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5949904060350671, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.29049793709903843, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5660059776713433, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3534252810313016, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6247144454333148, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.1925903910576669, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.45078285386741757, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.09941527806251362, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3375800400832725, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5942391703945106, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7043046273012841, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.16373682488441257, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5249159229096783, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.29663479358211337, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5048860636204477, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3790331198369714, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5564797446076439, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3785063589496393, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.550653561798892, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.21798830133080024, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4809891449178095, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2543786873577924, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.474821633299339, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.29622254568370254, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5178269067077038, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3845687306448411, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3845687306448411, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.29013347578303705, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5229103695975342, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19166642992550154, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.45352405841136717, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.32978372103036435, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.29622254568370254, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4935676335226274, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3066439134043059, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.48319828737392106, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2991528889155786, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5582453237847728, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2139991547137325, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4401240520726166, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19681703236998485, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4641799487191322, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.011704493972392318, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.24391450136812154, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4188399581018156, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4784684190704374, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5220744129850714, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.454674783834345, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2392702601822198, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4504639375417262, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5107881984342949, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5397858290886074, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5616963280794934, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2734404217216863, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1014524997386625, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2953987627094475, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3946720316502292, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4361039802749712, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5269731605293632, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16170596160446446, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5772772631219125, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1354715470706931, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.40840642737172866, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16008724961429593, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3979154668239613, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.19230188007838597, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5927843365311597, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.19230188007838597, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5927843365311597, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.12577829595095136, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3358649233160436, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.39812118573723865, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.38327626440546453, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.43846037099743423, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5878523089199363, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3049156495560148, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.41208793236807006, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3635609139463711, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5425942881923044, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3727355697846668, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5366981850233046, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5063945134578823, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.42656860819541537, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.24422057337699718, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4745686548450405, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.28421103644630136, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4520674720621938, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3092676945859865, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.041718664057048, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.19774288940652704, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.002777777777777778, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.1754386006461776, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.47674964090612326, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.3619317454406273, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5603087309111027, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.17101456688527578, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.31396874406510017, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19313335507865945, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5370585235328835, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19337006497014184, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.6117839591567146, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.32161227721249164, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4889481341529844, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.03999953381673504, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.14295717937701993, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.39647338707491836, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.43504038103657183, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6606468296022548, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.3265516873506877, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5955775050987988, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2392702601822198, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.45083730819525286, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.7071067811865476, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8568176228429959, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.7071067811865476, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8568176228429959, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.8843865924896842, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.9546910250050761, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.6396679416047654, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8130954821598096, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.7071067811865476, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8568176228429959, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.7071067811865476, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8568176228429959, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.6396679416047654, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8183519585847914, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.4302123694194221, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6691232302814786, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.1736516517811053, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.7071067811865476, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8568176228429959, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.44689472642345274, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6588405895873823, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.5741156866422448, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.7600101685993667, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.12074172794466914, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3854432348491077, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.7500901713271477, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.8624598551416763, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3280740637235151, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.18975516698135844, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5467364890370301, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.8843865924896842, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.9546910250050761, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.26608125176434144, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4802266386987784, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2966090320349725, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4660692265920593, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18240162908464763, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.47352584565341405, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2872797668292002, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.499989214794679, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2872797668292002, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.537813488946275, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.27602580646531577, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5170713393917188, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.25916413607200117, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.48625815319476634, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18240162908464763, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5287419988380048, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.18240162908464763, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5287419988380048, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2737111320203921, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2698078272149417, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.1950703465484404, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3491985989318535, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.6696429767392259, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.329340597116918, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5811461544739382, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2872797668292002, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.49898853929554654, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.034132793984978135, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.24125513696128442, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.27249745234058675, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4904389092071885, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.31756072966857934, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.20658804691348367, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.30376137001310205, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5498110282118828, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.19696533992407975, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.36270408031098256, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4425219454479648, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3847693175443825, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.35479105265934485, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.6164147380135121, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.35223865745748834, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.19569434861872417, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5843699612664682, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.026164052754179955, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.026164052754179955, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1955775564284596, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.018686237228756782, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.08008973610668292, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3081206097311581, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.45267569576678357, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2928298013714697, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5433026792013316, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.31214672998964255, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08222779739686721, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3335295895031916, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.30052834075859, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5716680280251661, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.04331732537669657, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.006530825496342739, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.22509207586959207, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.49023502313124495, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7638414724136195, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4424906782646928, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.705507971295129, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.41452787844405115, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6973605663974715, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.41032302768839235, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6634154486532953, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.638057576753081, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8245673639562578, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.343041631179768, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6383283286161612, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.44711013370113256, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7319347493436125, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0941071492118366, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.22362542790697484, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.1406005899217114, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3205132145674765, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4275810014748856, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6481070648129139, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4424906782646928, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7213459154288302, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.28473824051926716, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5944159484469135, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5702655877666989, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.8232854345902009, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5627396123761852, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.768337575605251, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.46409619603227925, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7474126325188408, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.42803425515420807, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7260183442795153, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4361016861714566, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7150254604232192, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.23183344653730417, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.48766037123469547, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.23962966980870534, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5138361143222901, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.3597862823053843, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7212767938301806, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.07860105393900486, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.09678377693633947, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11601141307045003, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.21671187566850864, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.2390076354901812, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.33570154125476054, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1371661844308428, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.23455679137513727, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1809155303398683, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.3604670693910988, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.1775614884118737, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.21326369102393236, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.24781828193168487, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.07404009463634391, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.13528723418511077, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.08990845492237175, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.16528667366086555, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.12394460940540938, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.26662620996190534, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.09118352267841409, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.12596283258548654, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.10738497851825159, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.18430770214819148, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.30538115660133164, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.338864446519003, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.17287505598461764, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.24853382028634724, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14891504773093184, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2618919111168516, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1406879778177777, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.24227488458492952, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14399548544647026, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2528996799005126, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14876927210374952, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2536059288500648, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.04114212836378985, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.1070604518443882, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.26411327741267115, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2898946819245943, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.35015224715252113, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5701648579139658, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3349252032650068, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5908087431574293, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3258812297722265, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5753985304712377, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2883113322808919, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5835478395499368, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23475000928031314, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5032853946032531, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.11690741296020518, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.44984705715342654, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2577716972449781, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5171901208397282, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.16424155566323012, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.1781207588347241, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.04631732527976412, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.21558480215297515, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.006200396825396826, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.09350604622460418, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3430629209966263, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.25639784746935274, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5733913952323451, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2516849730052866, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5441146119043165, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23287896954139942, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5168980964497457, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.24643585808835486, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5459613462641708, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2696398422206727, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5506563869475618, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.004578754578754577, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.004597701149425286, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.23325505861671614, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.503948422566616, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3449058130015412, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5365619830343804, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.29688845677442144, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5494319015457763, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3257602417321556, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5666596539835803, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.22511140285349446, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.553839023223762, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.30298632514306056, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5652374402593988, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.24479697566202357, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5213023098886357, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3274016883618531, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5570399656004248, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.11114096285893173, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.2723973389546046, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.1196425813555299, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3031655363777367, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2211880505010663, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4573855767208229, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.1690653646485627, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4758186156150245, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2708105005235697, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.49508133913561864, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.45149688763848994, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6166500596693574, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3887923654575486, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6140755432780003, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.399477857457097, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5617218895807364, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3191349966700777, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5329750656706205, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.2931154738386615, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.538531089380228, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.16891395122331324, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.43166826352433957, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.09175663647957763, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.32499940569388225, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.162496560019558, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4637542439867255, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.25376032254696296, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5334329403985332, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.20039141607873007, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.36123312088832493, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.0564437248458207, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.15026037463138217, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4303467795130825, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.32752310268966434, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6168686838238246, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2529076741385625, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5430833248313275, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.207314191412716, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4360555836773355, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.2897852141814925, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.2603665007398762, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.08070632004040007, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.35911678207067443, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.25288574410850384, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5715569142855546, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.29537010291406884, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4221671351559825, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6302060108035411, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4545481795400536, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6054218377148394, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.4398690431123469, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.6046405925677363, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.24968557018529272, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5511430757077329, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2864021858368971, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5777536673857124, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.07833614957377547, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.2978243697131122, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.036093834539820895, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.1939545119098376, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.48320036215224016, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.32707695373369694, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5166643606783462, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3069937936246452, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5024648105961349, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3575909322256676, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5409483829147745, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2228729825024992, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4466759653076362, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.26629603567533056, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5253549608514286, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.28261688976967947, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5075237416590358, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3235473265529593, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5441122251341168, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.04595467899356206, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.2598586520351841, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.16787356943023207, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.24761638648350678, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2781578586520005, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3796663901127053, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.46782343515163066, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6422853411921757, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.26403796477530145, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4493814923987531, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3935019932504074, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6071903247613194, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.49341196686542005, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6590076259512049, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3288143137394372, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5596092732231619, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.4122335241726334, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.6323888082640657, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.4117440619621889, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5815106363300868, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.20576804883654082, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.37723120852370196, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.12858902882463447, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3148709023566568, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.17140863043800483, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.39681418211766745, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3927237741677927, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7451438087039315, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5570357635362685, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8116469942298856, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3508597296865219, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6833592152043626, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.21259470439331316, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5863866793721222, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.44340494695017685, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7587103444385384, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38084051173962913, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7334510090568515, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.26513488970168847, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6029932145447834, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.05923625523450714, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.31569765163635033, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.12062355101812712, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.33811435144101354, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4432782054917686, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7181569025811343, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.33282724824658805, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6835909948825732, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.2646692275116123, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5971551168243227, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.6263164471220594, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.852013904460107, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4940317095722323, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7362898909098208, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5112867162620864, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7497537018148864, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4667782254569818, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7754094279644977, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4667782254569818, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7754094279644977, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.2359102917931129, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.46234028881356193, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.10177931989613292, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.3335479382455017, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3459167762620119, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7155724078484401, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3826576187198625, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6071841372061269, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3447241447679157, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5531085140985558, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3178743908080705, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5513949312034092, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.1883251048230039, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.45303225382772006, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.019298976936385798, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2378706071654586, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.49630155585737695, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3860973950960897, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6271680934322363, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.12899691256037651, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.10255693412858163, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.24967756802190116, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.559682285505658, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3157197679655673, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6311766762942234, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.42165893179697905, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.36440851219076265, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6157376412237141, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3969398322556475, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6236448690964278, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.38048895490051765, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6349497388372479, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4324371049196428, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6305851137521162, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.4396289179879654, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.6487399259023146, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.09896281892480713, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.376192516493049, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.01937817581496422, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.1805414152287055, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4894585255537274, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.31128635710849173, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6304411194127884, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13308561809919006, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5312476702183977, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2579124920342433, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5545120254366757, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.1595487507830045, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.45111566089364774, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.23693055763743093, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5928508275621333, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.16510868745008767, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4762714594756596, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.27710310401156996, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5216248191624099, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.059703448812578594, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.2883367116290346, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.04503583575448186, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.28569900523868325, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.303998162324503, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5931856951819833, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.21040286183905324, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5464826942840814, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2493264171390761, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.46012273577134766, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.40696144066138723, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6476222098586478, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3207863467056968, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6030950695494548, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.39631066492420963, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6670602127484115, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2625805454451497, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5886806140244891, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.30857386418398147, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6255460002189321, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.23301500681900636, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4732064514809435, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.06797010899515823, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.27154181329396565, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.19568007857684672, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5228407307909605, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2879556779114461, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4554184077174173, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.09578921953028982, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.40472887922389433, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.22965669823067916, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.46247819390492995, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.08920952468433085, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.32241875701400735, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.06598288291076504, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3008263306617865, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2059931729749887, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4491812480433597, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.20475739007221866, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3934874462686164, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.14091087674113076, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.129931470576492, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2945993949560173, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1719646079342664, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.308102700736633, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2534555198498905, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4514808121244451, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.09278864176093975, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.29077212346360004, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.35174128537520233, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5232532816160403, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.29989984326599584, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.45201602124250284, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.11684343186914438, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.40293579310759836, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.28255079601170635, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4828223682720399, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.33089917159160825, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.49423984666314635, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.06881975883969664, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3087076022347511, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.2023651649328507, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1689706894436884, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.32609144958957464, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.38729516708438194, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6571482446395243, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.32995628251235876, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5982616321404195, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4381454708258676, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6163746220282033, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3614922712385951, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5698489012763526, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3957463068583885, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6093311944617019, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2572958792096885, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5064333161464132, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4730742700342366, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6716818492415609, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.06730826637437216, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.23959487558830286, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.1929800091551954, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.37705878363065914, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.41278042192714015, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6060858750149657, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.028718620586134988, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.06819568935771328, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.28398527281580743, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5353252373488673, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5839068685770862, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7498987134962192, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.03231618598390566, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.018372817903957082, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.568128598260769, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7443891530963911, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3915774240356112, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6438987110697019, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.5052922639977637, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.7104337168657513, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.39901140710995353, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5456268880813968, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.17827215716412181, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.31830622503514655, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3173241691310352, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5910464434099775, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3665528144045068, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5966563047685359, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2587297749908005, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5132023401682766, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2914897522509679, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5714769597200869, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.11150937707712508, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4170915413269471, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.12061207067450011, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.46638924840013024, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.11675747661776523, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4301556378791635, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.20057225201358211, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.47576367606491715, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1169017254476769, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.25243905051959625, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.07539975290981413, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.30092387998871956, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1078517242048809, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3886262536746606, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.09282999600999915, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3602616614804148, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.08048862002869049, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.38839838380229685, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.30250421218183904, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5314198518425818, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.19779406326150695, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5032281717452601, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2674907183014193, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5237435675958946, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.21024692077841572, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5403945194972577, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1280398105600789, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5140283032612094, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.31309813582314194, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.026104354115338492, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.18449230121441001, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.40058346018376356, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.29894673648596126, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6322815922673689, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.18330256089173447, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5328391139635578, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3478966138007723, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.666271052510266, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.21697301406549346, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4876777357531764, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2907703616727677, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6671226464299455, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.29019765706301537, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.598596485843401, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3151295371556651, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6242597159052685, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.07145977539457268, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.30420200787580826, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.07487205965472855, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3134735005064425, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2672991324984635, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6474323586139361, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.28904496671735136, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6205783309843279, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.12521098911929102, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.2534584650774572, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3486251970868468, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6519074063738273, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.31280763439438314, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.605102269641409, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.5047460217572859, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6981561913726569, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2622053872435742, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6045462235214704, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.25014180241386386, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5948201299027263, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2258043389079604, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5033553487331558, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.09841955325773799, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3327723902928814, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2615651536220919, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5337436257798058, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.7416488036617811, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.9156308978596118, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2924496936199556, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6040522123603048, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.35611859459201994, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6591871481895288, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3092067388523221, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6104451101668408, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.543070234136599, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7506439740838399, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.46290680573161996, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.688869111662782, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5295672450222603, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.715157413474444, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.07150786783833522, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.3509665568396921, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2173044897357899, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4571110459558132, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.33262718496001725, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6707552233208028, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4196855486150348, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7433904631553542, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2894921926769463, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6202383519071005, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5995826896426277, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7943692036315023, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6993946355159273, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8854180853818128, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.6176355987862611, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7898758502538201, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4475966481812816, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6848118022736988, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4559665634342608, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6856895897445419, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1488773345157941, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.3502460666032722, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.33625310520541907, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4899679589833683, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6996203149315261, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.23119301671666287, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.354782287640505, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.20419333453691463, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.39470297247688435, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.14599223028360678, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.28718685195806315, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.0680779227699037, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.29461063296452894, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.41177002362103615, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.18386904980839383, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3263831403119468, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2995728063785384, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.41824297302824903, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.14920276910823294, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.23372518880177304, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.15241326793273957, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2373874392211583, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1948950171081147, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3579044902117876, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.12792364540053502, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3042229576057812, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2423936863423674, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3482875559347012, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2409168844747761, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3760904447135035, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.19123206651963354, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3643868829217187, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2409168844747761, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.34625648713313856, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2646814749718951, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.38312949443875044, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.2919568084302786, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4097202831960618, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.22076059779174925, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.00882086689569064, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1753792879326568, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3388058023792196, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.26230609318615344, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5822825437641462, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3131514736435596, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5852253917268062, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.303083208699035, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5712741347584299, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.31961023654590437, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.624665235852261, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.033288372187425926, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.022279084478187435, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.06298574903914071, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.04937216027445676, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2356808688936941, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6055769871534641, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.07057336332240136, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.27794985614895684, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.05976469775528989, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.29483492026263836, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.2841435865247738, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4668115397161167, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.31925439389264404, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5392797996676849, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.29239744118171573, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5000428320937891, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3593473105345847, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5947494543532806, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3754906253392964, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6588309503016917, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.34059688207022226, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5628429966636888, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.41714597501205064, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.6924696604582061, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.30864757764602013, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5998796997663499, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.06402718864310818, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.34695960525493563, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.033288372187425926, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.01992327449241025, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.21510544667604684, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4846454728121982, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.22551665711721375, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5279805413050443, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1565711240691367, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5086519720619103, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1258220555845937, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.47239582679683584, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1413598390347116, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4830716882630716, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.03519816815769828, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.015973750745917652, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.15991187032000503, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4667629327672802, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.34259841795512924, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.585466128440694, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.042741233133146164, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.1133793152496745, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1497426195025022, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3726183841781829, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11435885039099025, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.38595569757978, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11740365232394666, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3950281226485317, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.23969951086481833, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.49980090988685105, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.19984031923399143, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.48490100132152725, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2610554047890956, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.47455871891673146, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1345609539980525, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4564753327718936, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2648638369801883, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.556024235512166, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.15781880138100113, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3627260973544584, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.03519816815769828, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.015973750745917652, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.04375436627586615, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.020262091842738417, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.08905591495817854, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.39258991796140724, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16839298730242253, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3815455050057558, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.22481285662586992, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.38610735170310867, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.07292639249248285, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3325364976906501, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.17743299460161882, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4899555753373575, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.19057582910221915, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4718416669109882, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1314770573188977, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.42247455964888564, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.09157767943752927, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3701460681897939, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.06669809736714213, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.21891089447825662, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.10803064316196949, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.07765674844412951, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.13507002547130284, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.24864356194242332, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2689259076280853, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5085571523284772, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2280292808597417, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5045187042197178, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.07998996525280747, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.46694300232895003, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.20686631979541423, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5414930563125206, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.21347288910540466, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5213180608720375, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3288154767854781, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0619525837309077, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.20810880139024002, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16925466459550803, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3398252842976541, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.34140765467102613, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6319466141042981, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.22592501932697184, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4846944833505256, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.2928926658121417, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5528145631801176, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.09861322169661857, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3428977474554415, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.33311017108029045, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6152393361388527, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.2647140242373933, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6038381731388569, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.2058592651002273, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4968187716376065, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.1847269092785415, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.1847269092785415, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.30173859880787035, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5195706056213185, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.15937946569579547, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.45845453966638194, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.15736573842205165, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4353622002928028, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6713478366673378, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.286424022785037, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6108160899721901, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4743785204576228, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.7078409133478152, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3456425407114715, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6437361452928098, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.304577696074354, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6169603629801113, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3352630033761681, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.2848709355004181, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.18282472485667683, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5027337480128451, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.24572492027154266, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5262167453128139, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1809849704111973, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5183477609966307, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.19464399422312637, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5198306336056712, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.19847761251706378, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4798124823955707, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.03599560515986058, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.016567810125787508, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.17500281336427004, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.44790575694816215, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2682764485524619, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5066876769170529, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1547981586771203, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3205200486955593, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.26485738863969893, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.004773082147669651, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.08292855306993584, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.04879296088278628, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.18031240328973427, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.07730946223161274, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3543827361424084, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.3583463145772598, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.597082260723824, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.30842328963154475, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5533832756338398, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.27287437521258534, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5680146925253824, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2605463938154069, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5612230499845808, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2920134076564045, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5696793890490214, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.09857802458552499, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.37805549635837926, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.23183643082360209, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.167234964196675, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4598224413569426, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.11543246428739175, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3867652322513648, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.1752510532254824, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.1096600595185198, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.16260441457252336, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.37196866466168216, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.296106081433828, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3348767210373086, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.21150430967143613, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.22520408495200187, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3055950800828411, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.10213889902359212, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.32878876614064423, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0854172444037865, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2822077407025544, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.1471731939801332, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.35613397842834366, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.09550255684070111, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3229718971488525, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.15796681910573898, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.40727924114728786, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3956940134405236, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.10482054709664401, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3662621832712706, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.15232399499208898, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.22542170102122022, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.27278835848187016, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2574866101628968, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5192222793733214, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4165851519399544, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5626264040219835, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3279697678478715, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.523740736836828, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.20079352324782537, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5138627523560615, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.44702012563994353, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5730388206570669, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.26521877043131964, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.41000643148292765, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.38762928139075753, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5446552031353901, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.15363941244107066, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.3041152734335267, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.15363941244107066, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.3041152734335267, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.30335178070262864, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5110748651753049, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3043760556486702, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5831741446799831, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.11258390959554744, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2499701253990355, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.41775329557815755, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.615048701615364, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.47252884345725904, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5979074937874786, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.4843113591527644, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6440496751909527, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3836378227271174, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.576300320227504, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.39081172824475424, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5754293696780579, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.26933264604451856, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.487526438995296, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.13334708422802907, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.32038773971038526, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.42383919356215566, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5611383064918709, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2062407699777119, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1636538054009315, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.27030640495259156, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2533935280076646, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.35639112162596603, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20469187767870595, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2562732501285193, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2193938326426279, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18968668542064138, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.07694262297493382, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.07694262297493382, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20980831111140325, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.274654868986135, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.07303863538896588, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.22255642770836792, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.11368320018193068, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.304990814668614, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.26596587645638975, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.23235431918379582, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1468128974935517, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.31601347678307357, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.28536974606932336, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.22448784282354864, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.10694329815809711, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.29703553525902243, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2905178491524662, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4540869803464816, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4416037594311788, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.5926552552596459, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.4183954028764231, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4906994718051845, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.014073100248363871, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.191952233722376, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.5821113312936593, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.6682049424481182, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.37974703287224004, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4784059073150431, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.31172573638980083, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.45166421390889583, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1878322123464407, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.29465564326686483, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.01445896300020725, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.329340597116918, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.45129224979788274, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2576254437408645, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4648884539724795, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2532199664925789, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4300207561067402, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3901440609455783, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.44745023619328156, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.03256664244421472, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3526878583155709, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4468173561897173, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.16652678576294083, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.32423547140462744, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21847844937497599, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3923992785132143, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.23724958596921322, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.35823441753358387, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.03256664244421472, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.29698362304848486, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.46177552759731727, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5441799557959847, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7471708187115776, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2737674171768533, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.49294682774777393, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.441371588380312, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6477253956590645, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2900657692103618, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5959886771662792, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5465033074804745, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7499074934704908, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5021429409594009, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6919014524613049, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4286493815549817, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.608929454341427, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.07225602892167936, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.29878327654661274, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.07225602892167936, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.29878327654661274, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4397080749292039, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7141130990691512, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3135342425916377, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6210817766473049, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.25803866913759976, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.34620959646598154, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5617489123817119, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7727913932943925, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.40676766131178976, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6956515361644989, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.6728450601744213, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7864311690897225, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.3717155023854462, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6551663797221938, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.5215099214730985, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7532497199234878, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.32534541934969374, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4626445734330468, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.13240628161243978, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.343946203604971, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.4577369372875184, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.7101415565054174, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.36092600834422417, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6496714079703786, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2322365386782331, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6044384701497908, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3064251318019254, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6182391877177092, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1651157059535634, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5582712048370183, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.22649932377430695, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6026783583939563, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2039057030112552, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.571035829197345, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24691200113491704, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.594269344169987, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0911356222075961, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.30976821853610853, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.08737167851715875, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.30581414833940024, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.13652085900837302, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4761370326369281, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.15474877339130935, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4712355780453016, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.10952542777192922, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.2783128399737003, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3042729202167935, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.631636824383677, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.4059763180954132, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6572798986279489, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.43275966453933684, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6405112835577158, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3768478744790068, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7090128776983943, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.30905953562470256, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6622367498379318, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.13149894617910776, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.37815587581761695, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0033887281254162717, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.04357500712552422, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2362700080032879, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5323731887249256, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.21605302662107204, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5282568801368064, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.26458538438609513, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5387766932929448, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.13324009269060547, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.43938753038448325, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.08360795151624724, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.35429954345961984, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.19635248523500579, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.48914706397531627, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.11014333487863136, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.41120665566191017, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.15435869219704992, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44156603809589606, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.07222837169226046, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.25549328851755854, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.04402492652225698, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.24550650014690958, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1378413097704262, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4211572191546224, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.24870720433450894, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5735974400415592, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.013817287974302723, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.12536446978204066, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3457963945572483, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5975923648401492, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1444220103352306, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.48799831725044884, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.10621549048619741, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.431831433985273, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1719308255245778, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4713105639084985, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1780606498214454, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5082580772086693, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2914965018091027, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.034101561447741305, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.1264811292086546, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.19703715011933906, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4326807387314957, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.07228800742761465, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3524948213332762, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3972317449044497, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.409648387810045, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3316829223225589, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.0041614648356221385, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.024012200597804383, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.09757710283079672, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.41975185347384797, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.12115369824118394, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.12115369824118394, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0791188256545285, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3180943786872059, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.01809539866686559, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.03594918688245323, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.27586328218418676, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.1113631734978524, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3741979529200897, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.10259158366128554, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4209327448560267, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.09528067873060077, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3544690292289135, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.05038767655098835, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3585941732179629, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.09230812022268482, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.43002721697522195, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0743936478408373, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.30237166895145057, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.0041614648356221385, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.06967699606840941, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.30067645885474037, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3972301056942388, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5673240077710876, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.27691593390925684, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.397254897780366, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.431440472360091, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5867820725582551, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.33370269242604067, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4403514506678736, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.49134520717123853, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6018727487732392, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.43276672055758025, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5477430910654226, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4516989732837159, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5415798785310697, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0818695212523483, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.21389006966831828, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.07468025823787741, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2295572628550584, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.27707852552725587, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4017475844016888, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.39805634587063443, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.48269236653883857, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.09896266491372588, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2200451105194662, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5433298898255388, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6539235920730772, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.5092920820600262, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.7015498636340426, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4868801987813637, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6780031796193685, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4807632521130567, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6004276937762728, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.4386676743039076, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.5540223698738236, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.016456805312687214, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.011389062176759937, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.11233810019914323, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.289567843960365, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.48640235222602146, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.6149323786242455, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.37566372103146395, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5970100838075844, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.37989456711162206, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5769558960935135, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.23324427100847284, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4221129348893475, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3115230560624543, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5400649415883527, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.019065204285618847, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.04824196983803427, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.29808592153996283, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5278034227464174, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.23667062365446973, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3073763958460875, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19054540236783327, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4105353806160392, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2360968429109492, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4627612219764735, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.146556809091633, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.38590997021162093, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3895672786514209, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6195204168074118, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3509814893708312, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5555382601570973, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.23953300557044352, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4748663920110332, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2705411345269698, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6382727936402589, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.26165878484802635, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.597371720013285, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.08593880254067122, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.393760656889682, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.019065204285618847, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5136268735913038, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.747250567370702, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5269786261674732, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.7211839703961767, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.44704175546996683, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6464230283099384, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.45718323554054785, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6782668461340563, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.004290004290004289, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.024707645668534613, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.19943370880401756, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5118140585073162, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.01120180139519698, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.16357632783064235, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.018788314098527933, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.17662910365872764, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3688451938640129, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5612443053901701, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.42119189271590934, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6000905799312327, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2192051105601272, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.474604589222231, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.5977584263760277, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.8063885917966144, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.6868497310757332, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.8147345977692317, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.42149530038712396, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6765855139833816, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.47380853976119175, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.7354659271412988, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.501032405276633, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6978436898290393, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.07039178869925088, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3262556441298511, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.004290004290004289, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.22407318098839504, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.44990431651746765, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.18473000217570404, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4760100031203425, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.18239336435292994, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5029345390359463, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11379273899572502, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4217370584767284, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.09486793917477333, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.40615685666658385, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.22878603824610966, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.5140335091788867, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.10500646136500086, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3190724849310781, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.09697472565363051, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3745932362705387, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.04269647757530258, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.19536240230055701, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.16809999283143534, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2738834400667501, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.06527413669170568, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.0691742922954427, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.48148276729321016, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.6931006881700985, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.2916733028854906, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.611629344099449, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.16688708659032603, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4728485884522032, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.12970181521722748, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4710457410977096, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.24709901811909443, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4876426822294573, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.08767210132815903, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.38627413137459216, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.033288372187425926, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.018468643623756158, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11695317153743115, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3888506293564944, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.24887831362342314, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5200881906842448, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.24135344239900156, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.546651751367433, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2240750868020436, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.504592024551707, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.19599054363136678, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4875379508385634, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2297794059243321, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.573570222814656, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.23694057839415494, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5263543431854344, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.25259068609065677, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5384891408722134, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.14728710728025965, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.38144450027069415, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1398394229916333, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3782539243445202, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.11823191425473403, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4539200739128128, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.23499154120415805, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5277871993658991, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2327860836832082, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.30346043520808336, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5927380044714227, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.27438453676673524, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5889486960419529, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.26609880387709, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5830233490543315, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.23215933493807642, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.547665794111277, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2678221046101489, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6016268776319008, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.11478040986605546, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3672482256653862, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.06668493248636373, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.2624825156254661, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.26361106287028546, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5611266753056532, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11290965451231479, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4125077608038444, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.09225101275784285, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.37350112612982594, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.046937320085945096, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11898263078627454, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3841920009391055, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.13824120769041665, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4421654273346281, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10545905769586214, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4263824758050386, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.09561039442149676, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.410158328815622, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2036855110312808, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2036855110312808, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.009367682811159305, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.07902025848436119, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.12704269942859717, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.07842372770674794, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2577072248185967, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.2017781982444986, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4593303345267288, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.09289951019771917, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3765328870870861, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1633682038712857, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.48014665724836264, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11236616407443269, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.46893250816271476, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11106691492771066, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.48722807515184047, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.030634941698807875, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.02648378925084961, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.13737279171076758, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3592365999197816, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08961889092065865, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3874168292468809, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08100859619233457, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.24451849449561322, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2601769108810108, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.455492879700213, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.32169697571790584, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.4664391558122101, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.6054203380219411, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.09367325773640851, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.2641613455898965, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3471239643495614, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5206611437816837, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.13840054871865481, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.08099386688123823, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.16164940677303336, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.011179312292844528, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.028853119411472547, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.06268260360206095, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.16787977700016696, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.46635476894028405, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.6673933314595045, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2650114714119404, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5109139879921593, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1860799414745892, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.41284800811511635, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.32766922055009523, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5803713235003094, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2967631506608853, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.514979965349806, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.008968578184240296, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.08102231277620507, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.015082985407569366, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.13391621912488938, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3410315731485724, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.348007986647201, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6148736550683231, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.31222258402876674, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5549937870516303, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.2706573913259733, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5619563043714905, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.21331098311931576, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.47660259733052845, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.19850823739068116, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5129122522411931, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.19803162353826262, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.40808208228398596, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.22816849039973935, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5295534280606148, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.19496249079519765, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.333772018311225, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.11856660123276004, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3380794185743489, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.2320305803246989, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5719371199531044, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5146400882255834, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.4917500979945503, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.3407563025626974, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6182648747061787, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.32263864160302524, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5545705365108862, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5196627001050362, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.27048170758554296, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5452157067944216, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.27748702735605824, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.536627470224698, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.12259149958656422, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3778482967548029, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3324437360240581, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.3472164938104332, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.23683075175361493, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2631328190836655, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.16455392433653304, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.13673885815184886, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.052821402483564636, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10721126066665879, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.13492461680840023, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10721126066665879, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10845726335944729, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.10845726335944729, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.20388486867467934, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11458590842196212, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.08003952569169961, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1621568294816267, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2655543079691671, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.1441134993558708, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.14973178994918127, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2143764616947716, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.14632805533902102, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.15249396726488093, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.014262006975939606, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.11557977235371186, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.461597801606675, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6280777654467244, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4224298950114519, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.60823085524287, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.30451258861070496, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4983778740634126, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.36033217429111203, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5707860320039717, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2826845419324588, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5045089092372385, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3040559696901293, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5057907399711822, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.28950110908559684, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5756159459598353, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.45886678012586496, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6234514801756209, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3916177035633811, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6068458202737596, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.4378159930752921, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.6143976526783714, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.00815517427893749, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.15465401249808575, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.42501995363729067, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.30004556274899286, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.561482333900969, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.36769040719718776, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4064141882459388, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.34722897369611144, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4103553163121394, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.41559381311227495, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.37440084690294706, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4141871474340027, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3685328560625331, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3685328560625331, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.36586001924521905, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3498976319211564, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3207894212676468, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.35316499124143624, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4170508650443324, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.44328515185259987, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.37150797394258683, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3707104995519665, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.3260490458373974, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.006130367300589213, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.29038853710161877, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3286711939680359, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5944310794747374, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.13547277341758465, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4830189619506113, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.22970092088416938, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5537467826528029, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.13547277341758465, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4685134392551311, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3498215108825767, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5324168516214499, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.3359695440470467, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3096036988813059, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5894510883198948, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.32162444235121623, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.47895604751385984, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.14485138702678432, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.39103385983908495, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.14957644445778928, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4378856092523028, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3212752586558014, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5721988203556037, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.2219217084770335, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.437742810290776, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.621154967713859, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.28507621418290774, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5782236466585765, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.22481074167380632, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.49840634234674935, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.26751157705127454, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5494472552960327, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.27601456328057256, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5472296545526177, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.11902363807507334, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.43385588622555793, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.0066610108556241394, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.22536453058221606, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4365811373563711, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2822535302220024, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3874773378787974, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.31747697264511426, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.40797778663955364, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2822535302220024, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3818556455365969, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2822535302220024, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3785761836985817, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2822535302220024, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3818556455365969, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.28336087141473976, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38214734777528636, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.23841754841770157, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.34481325534410395, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.10085385750978454, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.27755272407546105, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.09864534161806562, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.27758211935930016, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2822535302220024, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3818556455365969, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2807763229912453, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38395145132718883, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2404134303620743, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.34491830800436335, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3266011589665084, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4364077249430218, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.28336087141473976, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38098278649128375, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.24796413807329218, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3530186228211094, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2807763229912453, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.38395145132718883, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2822535302220024, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3830564706224361, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.14039809832465663, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.30143568945161137, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.07218766113019179, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.24018250025773352, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.2096419313570871, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.46935933364934335, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.773055573548356, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43368945552925614, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.640995178057518, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3681829215408091, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6273930299436508, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4389321784429702, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.646847036932526, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43368945552925614, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.680579963615687, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.13857910426205777, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.41268771676068494, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43368945552925614, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6793717376740783, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.38993131397648445, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.38993131397648445, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3595137194874952, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5619162673780028, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43368945552925614, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6377690735568077, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.10511846841633776, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.3307148671232673, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38694317759010316, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6962124663194352, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5165413230188153, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8152163780784537, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43368945552925614, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6793717376740783, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43383878173729606, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.721993849834018, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.35410595762404473, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5902080019243605, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.2710444515972649, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.007378883018336222, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.16440791304482247, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3160213610127146, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5165614670038283, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.30758744700466467, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4684197705189288, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.37169237058440824, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5383668331525606, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.18655267161524258, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3640275543948514, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.14200815884333318, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.37043264756085653, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.18384948243517193, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.40935288248313256, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.20050320605789015, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4046291070099031, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.25149980262171323, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.25149980262171323, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.14579837024705408, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3459916112351503, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.3033939025154451, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4463607309375049, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3233187869272926, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.31638337148949686, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5386981918746817, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.31518520840312125, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5072004558983904, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.2761603007895394, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.49207696507318593, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.31518520840312125, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.5072004558983904, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.13170034254236895, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3663183540703709, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3305034076847283, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.004516711833785005, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.16951909200513385, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3380125247643079, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2961516536011624, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.49803924348035766, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3459667618766101, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6170810606402402, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.23623790626704147, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5441149448679464, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.35936994872479583, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6492026440953677, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2989025112582411, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6058743571913613, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.1280220256953781, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.3766998614914371, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4161791450287817, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7054426787013603, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.20333448190047881, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.49831934768554476, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.20333448190047881, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.49831934768554476, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3254455687469726, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.577852219465442, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3387562718376491, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5665592722380606, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.13267656524657334, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.454151879254267, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.33667089470100775, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6074301230157959, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2812488198404138, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.569576589771398, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.39688965270008814, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.646373332434726, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4272870063962341, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6682855797405902, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2934521273973611, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6135709647187009, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.1477219991186121, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4266201924661047, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.008777992747819234, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.12288887055424895, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.4148619356639114, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.46832763312452297, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.8176110134774669, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.9436043261706615, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9880191679951993, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.0067104198717751464, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.9025232868361638, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9169897590736298, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.9234732618882052, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9472986863542112, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.9709835434146469, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9951728990866464, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.9154051169199643, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9757471794927451, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.9154051169199643, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9757471794927451, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.4888436840107989, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.8291158208899767, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.8935248372106969, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.9404428602061264, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4593546097889176, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.608602146246901, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.23386786214190372, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.46662929903381617, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.16341242314728613, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.40072549318878165, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.13952118378975725, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4030284875466178, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3419664738551679, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4989057926975962, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.38985048513980286, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2830789070123405, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.41858897147271634, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.20130088157694537, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3833494604836931, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.20130088157694537, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3833494604836931, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.1958598294695433, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.43120286814245795, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.13461801293778908, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4435148347019696, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.3120938792834416, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4489929043142396, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6339860404289296, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3419664738551679, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4931724444703712, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.4844328956731527, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6798474086331312, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.24305650182597577, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.46912278832283355, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3674668904964848, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5894468068684346, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.35230796576188245, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.0064546295242688114, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.36092853787943247, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.3397180516736864, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6494995648532881, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.23811989337799513, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4812080785035883, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.23168799483443045, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5252672120228886, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.2889285495431631, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4536746865348185, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4136211902049899, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6393493534857356, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.17268932789342512, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.47806194925419343, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.42067720018268145, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6309653612961436, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1333644800640392, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.37482189565379787, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1333644800640392, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.37482189565379787, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.24821926635843994, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.40551062972908847, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4501073963060717, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.12049514584750938, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4795015038022114, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.42382856047421374, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6321659688090209, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.39501632817024007, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6461322924967596, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.16310121952537132, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5625465668278802, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.4126152034907945, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6344543163574141, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.29340680870384167, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6003179769986429, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.42347099628764207, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.0018234865061998542, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3722685688714949, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.255918614113723, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.44318862516624546, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35285733014385007, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5945202859296662, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.34940338846112967, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.2506708132952771, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5592183664602846, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.25535827794051513, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6051855679458406, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1528571341245854, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5481360183906401, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.22166358657237664, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.45834104234305023, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1954411146921455, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4036830499128384, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1954411146921455, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4036830499128384, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.22478920073209205, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4500155517039222, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.22166358657237664, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.45834104234305023, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3439068946997751, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.37219737664729546, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6020217844686402, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3552281813814547, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5990409134152898, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35285733014385007, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5945202859296662, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.22478920073209205, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.46169108941910525, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.22478920073209205, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.46169108941910525, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.22857472921416747, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.46051531515770805, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.005304235332926387, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.3330162771465545, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2809009542151822, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5819888906713027, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4573889291137309, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6974989991762017, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5409314026600619, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.8023475129738281, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.11372027710077005, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.43980817368282343, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3615855225145535, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5942403748569466, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3323217739558646, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.65584145837095, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2460137257692754, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5397894338370378, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.16331948281960493, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.46281592381471465, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.16331948281960493, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.46281592381471465, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2745762486209681, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5421002898382512, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3925121365052661, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6435846290166946, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.16927318970546587, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.43090641888389697, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3961867597457338, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.654720368848453, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.47467913885027985, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6998445450956154, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4717991357336539, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7489646628366208, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.5170969057682974, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.7999241778608444, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3813707100324891, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.6705221264670493, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4009045958498119, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.006260653272080335, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.17193972960972626, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.50925856841751, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3487575221722675, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.15824382329465247, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2847034639706718, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.1307655887510901, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2688265704976335, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.010715460821011002, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.255774123517032, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3235165184655995, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.27185330211646, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2138567563219765, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2138567563219765, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2690830377349408, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3016154987854724, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.247428571279836, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.22537412722674852, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3609019979890711, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.22910978833981444, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.28534353976384025, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3383777404070013, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.25916413607200117, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.4126422185632712, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.3111725630388855, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.010275038134729863, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.29676390087816046, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.27914759735007616, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3778334876813023, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.33758329691923056, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4156592381734106, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.27914759735007616, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3453692248463458, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.21263609514366988, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.2685899741889062, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.19124822707796293, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.282934063502053, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1960019004146532, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.25373579926622103, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1954328575417037, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.30293053536483644, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.20717792614536482, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.20717792614536482, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1946191920482554, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.30211130048302853, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.20567299330048955, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.305308701368102, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.14998180732658847, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.2781311727915272, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.27986949820390616, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3524034144838241, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.19649146470411552, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3024070513474541, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.27914759735007616, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3778334876813023, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.010187697296954694, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.11767062888926026, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.2588701935884834, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.1399347491019531, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.30906837940069837, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.007792914637011044, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.15652048829355256, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.30581515496876593, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1196671345116598, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4250373762074513, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2805776238834007, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.37464507476331055, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.27590775387590455, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3308083900531814, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3539896048133756, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16177172185899982, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.35656294562478846, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11515309925749272, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2804443217107937, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.23638531153934428, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.31895726376311057, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3821381273701999, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.010064648984723833, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16496938783065193, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.42948798933258475, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2798876939782931, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4858922583959152, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1196671345116598, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.42091448842491763, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.34861239437033315, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3458399031409789, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2786084204986201, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.20810330808987174, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2303364277054624, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2551158426117226, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4338792723307896, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.15426765696281117, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.36404432411255067, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2869066874289222, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5218678198237495, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16618655166630525, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4518952099931083, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.24835336815593242, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5057077090166618, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.17729842264695017, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3991460047555395, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2149405271477231, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.40802426587644575, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10925297262553597, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.24033759271012042, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10925297262553597, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.24033759271012042, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.15337404749451009, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3658108225254214, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.16628701046894573, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4031359332940322, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.022674082413435877, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.3073229709775776, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.574087139172448, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.30791810312533313, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5601926721019862, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4511589055888862, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2434623104231637, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5966001227386803, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.27966356291643857, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5478435692252245, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.10845182904139573, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.31173251865601403, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.007792914637011044, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4091528869755915, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.28859523083492383, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5243060035864178, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4258744680390019, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.678077932919771, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3964513253420688, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5953388302269752, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1815358071299676, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.38935610444086793, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.4884391791679525, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.679307312191218, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.15980518115118317, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3462061115860011, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.35138749399652214, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5764814746526004, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.16771930140892102, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.19857943409196785, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4388967511840155, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.22743363869750483, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5072109323538316, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.16749684977011461, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.5366411241731205, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6918385856485405, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3423375720396189, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6262531466543148, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3091394458025272, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6747861905645746, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.022184632732552174, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.1294619581457805, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.3243466207565264, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.6005859006330247, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.13796620851017113, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3567938875935946, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.007281902334909347, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.21686905466335824, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23626187156344583, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5259172349664247, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.14065108796517406, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4653016103437884, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4188525447915417, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1251768639938174, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.39064868761178284, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.11847662670132668, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4766412062430795, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.15578519674093896, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4636631211068481, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.20690996611611379, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5406044734296481, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.29399556903245094, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.29399556903245094, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.11554716243103427, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4790979457669554, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.19312720381560924, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.482135799730948, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4908356678958071, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.529525057741061, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6698621490778723, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.36896156718464784, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.6019015041179977, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4295721431866771, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23966219681055514, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5979264101215074, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.23966219681055514, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.612884677361467, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.25830145139191246, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4896048354612968, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.006778644903960927, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.2846692049142833, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.3637736731596556, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2840158072494531, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.30509181191098333, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2674112241085937, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.26800693547499516, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.25491743114085297, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.10556737722881891, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.14053789733354333, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.12201842178576372, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13777657698404142, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.15032184952222774, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.10929637020896284, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2609493813392874, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.28145874884789657, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2998660085346492, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.29614096401881523, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2410288519041677, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2970891902334263, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.13122372520872347, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.12459914499732376, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.2338987151311022, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.31123452089299364, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4756674690337691, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.18506115334020554, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5096863469728294, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.26626928257104715, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.49325487167196663, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2579969134044562, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.14919322440986654, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4210541594444331, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.14669785543513997, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.3937770501596208, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.14669785543513997, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.3937770501596208, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.18634868443385502, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.29586489665278076, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4674087352393852, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.15833672839657353, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4191767182334318, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.267475684709543, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.2033250076872028, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5589196418579114, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1497342212184862, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4249764678866116, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.200571466871073, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.45594166666182867, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.18506115334020554, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5096863469728294, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.18439251865842213, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5106980996855047, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.11394659250985378, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.3384585010539326, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.007866479925303455, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.338607040915058, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.16510653858282376, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.14514613027046297, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1479818938322678, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.13842309322242968, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1025254666917686, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.10386784995254054, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.07271633793961262, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.11596632790546842, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08880223379062127, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08880223379062127, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1302790809384548, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08208180311085098, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08880223379062127, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.19015931169221686, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.09176378853337983, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.05932404902368635, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.040354945223762775, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1253385069411426, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08722222222222221, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.06084090533083763, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08316107357532411, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0744575238654659, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.18081240117184907, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2406197931700809, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3480566207137981, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.3002086140405867, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.4112215754871572, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.032062647754137114, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2188350647878129, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.19393255454120817, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2188350647878129, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.24181257538464912, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2727542434610149, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.24181257538464912, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2727542434610149, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.21241965502986587, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24856075230680402, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.12181575762823904, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.23698883946199675, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21099108137460598, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24619894242367388, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1561508712265784, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2966884811633862, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.16012807922240752, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2825590657535655, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.20992240303256396, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.240297594424442, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2164643623146457, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.014140612996263338, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.10958860302852312, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19089395298343978, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4775461600364851, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18762960550870147, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.505905280342391, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19843246352066848, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5254585376129028, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.11358085943578489, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.37976315415300393, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18762960550870147, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.49348230695305667, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.26766427098586376, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4581555129477761, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18762960550870147, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5048762254598883, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18626300660245443, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4752534997380396, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18626300660245443, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4752534997380396, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1847479638157385, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.49046945772456596, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18762960550870147, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4918089443050693, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.11960689244355235, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4380448627488294, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18796217698593565, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.47551817162907684, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19843246352066848, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5123967770684649, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19843246352066848, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.513009074208049, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1847479638157385, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.511165178065381, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18762960550870147, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5270918783222831, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.26938358189161943, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.46625322327819374, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.006565031463583203, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.28393900027333896, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5191104888927159, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.31087084319061986, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.48493403576578487, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2843877927900334, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5287507679912548, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3758626428491304, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5683038108649798, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.12412599390732966, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.389443562378031, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3375930268579116, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4797696968747708, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1930763338913091, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.34256550742622643, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.35540164109034167, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5028380576753965, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.19290431286720416, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3438946440208046, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.11998609496359587, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.30206893123564843, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.19028557421845702, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3481227049895071, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.10880654430256255, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3608349900973628, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.1393878237505104, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.435204703197965, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5881445232832746, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.46198675363922825, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5714763979586504, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2573016641379907, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.4456135188371608, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.23185691851902213, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.432960553422533, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.1967483629471718, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.36892641041012875, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.10199952656676965, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.34660334168484125, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.00622191087653493, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.3231291402565904, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3724134618099435, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5411724478620953, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.10991514729498916, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.35889788560857044, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1348135718388515, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4147071076319954, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2941203504244363, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1923965056241428, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4584215932853988, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.31291633863045876, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.15300252291898875, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5221038026847953, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2758817098791865, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17758569532749288, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3914970015153563, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.03744280238972193, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.23142549596796302, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.23987047142780468, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5083946276344661, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.26442043774364626, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2534901676236048, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4596959755675812, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.12645915844702074, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.45700241609605563, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.1955198139027402, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4488382703464876, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.00643824307525122, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.12179842317921927, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4354660335624341, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.32560507773821273, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.16402090918662934, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.14957644445778928, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.351130925091254, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.30229895292756775, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32013836373742083, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.28969342447685126, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.28380664599515204, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32374790470401554, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3319100075365036, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32692597326475636, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3003972271624958, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2947899275409462, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.29440875673203876, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3007628551722125, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2702894645159252, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32010751096684203, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.32010751096684203, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.21336052387554708, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2830838262503855, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.283868198184406, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.02875707772338124, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.20715500016834684, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2138028589526133, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.28819072249233424, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4281025086478473, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.1722187017293513, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4101544500733319, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15007225500722624, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3392953950658033, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.19587204862073598, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3104671471684385, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2461253685468257, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.39904238157881977, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2051692646110151, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3224454187442011, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.1784284488020755, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.28915891965402907, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.10372344027345098, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.2615059403670134, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.15072969952252693, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3087381774825622, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.13164235883295433, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.29495671936941253, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2879469254908736, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4591810337356331, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.20362939771829378, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.33399297886621754, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4683082256972011, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.32995315458175184, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4840937399079923, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3013756361449186, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.46623994476708375, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2639764334538811, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4159003903315936, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3023095132730679, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4131900681214031, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.037800765161043304, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.22607798722887731, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.005962033319367563, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.13419909715593323, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.31160827370931377, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.31643186523025857, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4990369740896189, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0972760643475914, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.34268917796251985, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.22851741162637057, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.39052360649350154, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11560300997546753, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2956909760018388, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.08749655303939702, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3126423887518639, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.08822997736304256, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.24974724440250298, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.09500509002957103, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3165301597200995, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.23609820045506813, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.22367402402736386, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.31291379562636384, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2554146380661974, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4265387920961467, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.260913547856905, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2494006679029331, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4342326033743038, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.2494006679029331, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4342326033743038, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.34936045232359575, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4829868973953706, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.12209516941390675, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.31861071050995227, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.30097206079743416, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.31498330380638395, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.007580249288701284, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.2029445207805708, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.29160060199573634, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.41859679392459287, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16457404825501376, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.33333438552725225, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2673465335275293, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.44086110954461233, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.139800134566647, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2819303243365043, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0775275441607937, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2751344778397747, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.008444418839629163, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.11183447695967942, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2981154499191547, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.19470810630637406, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.19470810630637406, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.22241585725803045, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3993550498239767, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.19469181333313726, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3702922644010077, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.09881511482966875, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.26151080011047195, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.4144465171640097, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49508811046905704, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3110891870529496, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4573498364685693, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.37070419185260556, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2756918913516653, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.39965414615166545, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.19775876971405587, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.35249250205040417, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.219417732032655, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.008423079864900701, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16832484320875543, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.2952766411314804, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.20614290043638034, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4026346891273123, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.10458125123016462, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36412391917812675, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3208902701740901, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3438619394909334, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.22495130162065566, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.38988663574936366, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.21883928293594496, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3942803458040245, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.279651701540242, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.41325325835097537, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2864494973378512, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2857216432461296, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.28755822790741375, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.16195919024831484, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36006146480614665, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.01004039572418084, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19086203703682342, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.40603556087396925, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.38060342997003915, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3652515753638373, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.19001369979060856, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.40380794812919807, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.15892913346954715, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.385345061282164, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.17179393697897524, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4061991090939492, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.010113508730872816, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.27234776738653105, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.4419177841121404, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6137680308213187, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.25567957494892185, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3876058827430677, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.27643937532700463, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4260558157086469, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.35933814503113937, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5180379308134967, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2676032275663791, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4724604738900925, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5001337105923725, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.39284822049881124, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5731994852253092, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.32244195194244635, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.32244195194244635, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4583677548612845, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.2864900351806976, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4754058246795019, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.5259681099822366, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6938905020324472, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.39615805576005414, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.625810777040839, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.39615805576005414, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.625810777040839, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.20296526946860832, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.40148740945870737, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.6136121029677094, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.29898984447859595, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.5666357652072354, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.006388648796754671, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.39360739118751503, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3914713795199333, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5396649879183305, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3049871822195904, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5208588286358844, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.28654756270464754, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4454875631569214, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.15395769745986762, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2834099674931056, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.3203990808307766, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5773010307507899, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10660282697866422, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3328907070225636, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.32284785906314306, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5391266648881738, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.12216223811537863, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.28630884247642424, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.11751163762525296, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.26392313732545414, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.08616885233894021, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.23536419207761525, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.07458227402640676, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2600891962590108, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.10704047550187275, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.31257857817030105, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5024602460502914, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.41452065364685486, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5450885611283658, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.13532043663194473, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.46999609081501686, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.04486784453363359, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.28812803702893347, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.25834168012156994, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.48011486442896073, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10649892433136982, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3005075192060885, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.007250479139228118, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2196332370857405, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2896941452360586, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.41709543651974984, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.20254179344857384, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.2105213575043129, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.15545256448255348, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1686298660722932, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.49742169356752797, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2801468315735759, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.4843599290976803, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.33557244321033963, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.5209156086024106, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.14475892711544727, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.16309206463693382, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.13194265905224933, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.15365844181846375, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.3886375628227098, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.567076716470624, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.19923514659353367, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.43916186094127363, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.10871164505221177, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.34283761263483875, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.39447879527991686, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.33419222746019583, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.16395982449057947, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.1134519688019252, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.15866683249809552, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.35536785937479715, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6031612036218008, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.736286703381354, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.39432344823662835, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5943452555220106, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.34437686643287496, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6090402109312658, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.39205580893266934, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6772940233934857, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4263005628892719, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.666576816248374, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.34303589686600006, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6476809000259773, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.43103580001357805, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6690742226623104, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4583355788727905, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6740129255664499, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4583355788727905, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6740129255664499, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.478854281434795, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6734455797843703, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.478854281434795, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6734455797843703, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5108209375191675, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6791666897129686, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4330463947479356, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6198346106486459, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.5730366636655709, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7197637548987978, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.2981426768485538, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.5882799317365235, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4263005628892719, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6688425476017256, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4263005628892719, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6688425476017256, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4485462070116169, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6460034217597165, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.4579102348988084, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.6417119032346416, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "bleu", "score": 0.6252078221435556, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "translation_to", "metric": "chrf", "score": 0.7406162627381982, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11254397891886614, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.20623288988983426, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1100081929352474, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.18967061672400035, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.10772332006118607, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.23609036869909603, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1498435848533153, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.21051700087939107, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11483748934907699, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.22187391438286078, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.13093265020876002, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.24423594551873207, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.10772332006118607, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.17652714369664665, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.09058415367867992, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2482894089551725, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.08409693408464493, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.24281987895429524, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1864036495127383, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.28188465375440136, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11997139690246741, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.24909548716299362, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.12326237503743924, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.25431387500879243, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.17755132725434278, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27939552769052894, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.11552449340806617, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2255572924690555, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1445047538382198, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2737322242154943, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.1957899789117337, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.32253417440653254, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.19989838721523703, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.2754449184617433, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.21286049738095594, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.137248043368656, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.22329074990170197, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "bleu", "score": 0.14969363386531168, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "translation_to", "metric": "chrf", "score": 0.27820986095394096, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.24493390281390082, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.48113625107113883, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.19476681308252697, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.42030407727741037, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.33600502687041833, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5162346121569341, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.10336049249219333, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3088863284587533, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2176929795148492, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.45404283402200407, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.16561315331829, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4491486313807806, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.27190910124573536, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5173567851798608, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.37648087568533606, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.1673300634787508, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.43009820921524167, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.09851325694216304, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3616605984753398, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.278818795864662, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4519726808757103, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.08108479333279653, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.32446242558225763, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.2985215837565239, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5357534811195178, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.3606261467953634, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5657695279587265, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.34854547753540127, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.5565027260893921, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.19593487880196195, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4136765523891332, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.19593487880196195, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4136765523891332, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.14455268344043232, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.3511816606173986, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.08839512340686698, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "bleu", "score": 0.21177781620127928, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "translation_to", "metric": "chrf", "score": 0.4460741740050364, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3459789902390003, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5620330456296532, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.37825713491091884, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5584414289480568, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3695375029926146, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.556875129479421, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.47923168144435746, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6534660189132082, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4200122602645879, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6060665795950726, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.3118437333980883, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.49789195197291464, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.429512074830509, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6066779955199886, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.37661083833298264, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5627715650901804, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.37661083833298264, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5627715650901804, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4257605183794877, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6026940597371309, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4146193110212601, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6016308462520554, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4185497912616041, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5947798105864397, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.39653893552930464, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5591087327390277, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.35456438094510545, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5476462735264316, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.40518022025671885, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5707666164180741, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.4257605183794877, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6072620760408021, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.42496721529949505, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6168976238774702, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.42963275745758267, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.6275089000554018, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.24287220388451114, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.4829182994799567, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "bleu", "score": 0.27309322054464596, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "translation_to", "metric": "chrf", "score": 0.5162255850430824, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.1845747513433909, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.44379971518505973, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.18212463619188357, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.469592540371137, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.20734616999079872, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5036833880605232, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2817686971402115, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5170853673805775, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.2701727285191305, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5162766222516658, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.09950615774798431, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4145753205477691, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.09596136927307748, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.40849147213099996, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.37365414901389854, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5663575595102016, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3931799632074899, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.571500205451563, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.216062485604554, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.4780977009860418, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.20768860794928373, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5045131603567145, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.19482672490156053, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.373972045369592, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.22546521673609302, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5396972089286257, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3347794278838163, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5836257841202334, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23502778906204924, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5533644883224328, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.3288562544630599, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5875530351959068, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.23858161101294786, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5352521385268106, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.22345694274330022, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.5021464201834536, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.024449792954766115, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "bleu", "score": 0.25748397762867226, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "translation_to", "metric": "chrf", "score": 0.49702079004924316, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2517176762753373, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.45137344500317134, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3128384316903283, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.48016279207050283, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.3508847643803501, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.529198044527105, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2674628639054191, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4784292149775752, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.2643715066746798, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4590454050790974, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.18555265687599404, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3943451217336116, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.22972631482860506, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.436102988762466, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.25259185051653144, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.42024044012027045, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.15765331776480065, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.1587543502252646, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4114443619817223, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.23252634497159352, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4176924459699904, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.10289033772949932, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.34792454493804187, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.35541324629951093, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.49416627591115303, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.38988999818957765, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.5383555577162046, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.267457541157426, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.4673846703066711, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21808070471467408, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3966492622645894, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.21011127120840586, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.3666764487561306, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.33305744607256593, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.26116607863611285, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "bleu", "score": 0.09196922936475649, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "translation_to", "metric": "chrf", "score": 0.35950194744727476, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.43200638115383627, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6892273787708799, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.341195158470265, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6539473951166187, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.47372467075851415, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.734800469477975, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5582838437615822, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7625459507115938, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.564140121947718, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.750543081695207, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.38962400400495395, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6039376140178496, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.45026965676007474, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6668256174353906, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4074412820541961, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6128620944765008, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.4074412820541961, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6128620944765008, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.310668922100995, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.58212864821275, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3894734858195671, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.609378229268181, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.51931843676369, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7468840809971427, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.729605098531811, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8833183865941937, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.3096348871649183, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.5646940504012421, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5585674160229753, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.791505922278621, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.29504037076486817, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.6837809127705262, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.48935454710294557, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7097085615439184, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.5723452380589045, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.7571087352239251, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.44680913024590146, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "bleu", "score": 0.648473971864945, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "translation_to", "metric": "chrf", "score": 0.8247818102038394, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.40475700826319555, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4349871720911447, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.47497024539412314, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3805666011451541, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.41589484475679384, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.38511373700997104, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4710260495003035, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3719027199086929, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3530084316582828, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4677317890018283, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3869982889970619, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0977318385642452, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4258156920135329, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3787500122126683, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3752043811916754, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.354353831625583, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.10235881838919027, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.42794399630326124, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.09230372260850295, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.4084071495562367, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.3777505211336872, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.09649622940465846, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "translation_to", "metric": "chrf", "score": 0.29275810079464665, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5244380103905697, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6914581279144536, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4472834999328078, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6457130269652316, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.403469748891042, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5836273992135024, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4521209970489246, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6307076431103672, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5201565256464291, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6663170490872967, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.431319746325093, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6367129659739652, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.310186302993101, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5434540129901786, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5844803970906615, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7063190919471397, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5844803970906615, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7063190919471397, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5201565256464291, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6663170490872967, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.3234262986694916, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5509482496841094, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5471998982127312, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6620274291313689, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5471998982127312, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.668797436013741, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.6201952806555309, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7357975825250463, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5950978682255068, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7209575532500453, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.36634140441362645, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5925773491774018, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.39359079123898666, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6064279839176828, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.5201565256464291, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.6663170490872967, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.2672991324984635, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.5378982230702222, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "bleu", "score": 0.4880149105083363, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "translation_to", "metric": "chrf", "score": 0.7177464929662396, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.504154287515855, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.6074467585243234, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.18771816026273827, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.37594160796244835, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.2828480467326008, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4330386622117487, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.26314173809974317, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.41943156806161835, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3180687407553289, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.43750976374662714, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.13950796967929138, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3461520644408903, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.17207258849758605, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3052503498954155, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.19047974638917908, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3156575555065382, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.19047974638917908, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3156575555065382, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.1377448219106278, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.35651447515721807, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.28599478270153655, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.500611405605832, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.24797752962743086, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3393109592089468, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5094767086148101, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.25578230816507097, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.45959138316050513, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3653634812607, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.5239315135469935, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.30019266689543556, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.520168227007293, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.3405782536352289, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4740333086460412, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.19955745890837207, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.4701104981474493, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.022925118914031796, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "bleu", "score": 0.10793991565723801, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "translation_to", "metric": "chrf", "score": 0.3418311350990793, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.33684416564135483, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6173496967095872, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.21054588509072256, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5020237474009813, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.21083122707088572, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.49504056885829906, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.22593581165006588, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.47811810874873667, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.365372700320629, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6006612018381494, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.23288432092807593, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.571224820704715, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.377949467106015, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6288808546806746, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2784369069281814, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5290670343764194, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.2854915274011029, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5160719090963704, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3335574881036169, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6172751686457948, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.30819625273001816, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.591546565802045, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.25393951817299554, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.46388056771039937, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.39359852091634406, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6265459059804013, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.24720109346452496, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6067542031388974, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.47194552522795125, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6449793729895639, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.10436839690765871, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4723697955467262, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.30819625273001816, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5915181594073229, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.25003907776594525, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.5740099623337644, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.10480708799994727, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.4347737895846244, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "bleu", "score": 0.3712375815038101, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "translation_to", "metric": "chrf", "score": 0.6205370332736169, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.11283678603002038, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5027560731174364, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.29432909534200313, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5637465580755235, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.20665163138245418, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5424961081814776, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3720123244240524, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.18586302203348085, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5550584875959773, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.1663603558532716, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5225044219427867, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.28341626687166926, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5869314876429665, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.18279722364340092, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.47825835330014377, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.18279722364340092, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.47825835330014377, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.34496242859007625, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.39992395664256997, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.3948810099417581, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.429294349316905, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6516072032987875, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.429511438817035, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.6426984035529237, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.19771661626342427, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5115994004182517, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4457322258249424, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4346320450539645, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.4980697864199004, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.008086388726125911, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "bleu", "score": 0.17781916046116683, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "translation_to", "metric": "chrf", "score": 0.5216356191979474, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.30894994002746395, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6495798576994254, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35806497640912766, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5522671396375264, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3391824705480895, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5823536571792293, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3369582032493922, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.604856884215657, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.21648792313483747, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5842434739000809, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.24078435074822624, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5511929774495076, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.23399485663908418, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5631067041333725, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1900264383673692, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5613137257427737, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1900264383673692, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5613137257427737, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.15084681924900642, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5314568462829651, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.26981967589819256, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5640017835905705, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.11911066129095806, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.441652518518041, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.31818246779032233, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6229693133713873, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.35190530004480436, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.65019529743538, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.28809973780460224, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5952046679740143, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3315037521841549, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.588148042382191, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.17403647602332778, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.4845935914407903, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.3337338878596308, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.6611983572472826, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.01890321292509088, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "bleu", "score": 0.1721831215207535, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "translation_to", "metric": "chrf", "score": 0.5841092375226741, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.25325897139464854, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.511461689033225, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3730973285213212, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5926422939507472, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.21478093144117116, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5322186790358018, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.27204984763557305, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5456825634559386, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2667533719706517, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5290480371370871, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.18081719101162075, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5207488300398541, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1793410088328766, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5126133936832279, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3585760940563117, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.599983086978317, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3585760940563117, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.599983086978317, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.24328420398524073, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.4502822427440237, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.12819160938600316, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.3968207935195225, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2846273713972197, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5068034604649062, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.4008628432878983, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5958332944294813, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3938117685205575, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5683065750219333, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.41505282193631027, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.5557512735595823, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3369338116697911, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.593905704810687, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.3369338116697911, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.593905704810687, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.1852365018195853, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.450559932956108, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.07367272607925157, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.37211692202201907, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "bleu", "score": 0.2571225648472028, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "translation_to", "metric": "chrf", "score": 0.48544337623818506, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.9199349282509897, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.9199349282509897, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.8827916928185874, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.9278293769424701, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.5919743410620021, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.8142101616656354, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.2762822897608569, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.24942094354139677, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7065161304293469, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.8047179188276988, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.23537164857894743, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.689799263500028, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.6642718379939968, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.7768492311706325, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 1.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 1.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "bleu", "score": 0.7660237942267061, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "translation_to", "metric": "chrf", "score": 0.8523393041110139, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.162496560019558, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.47693678197649336, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.21126480857843466, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4132516611502927, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.22654272969286518, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.4258225502326524, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.38876834795530796, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5513827117332133, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.16042342632389064, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.46873038602962747, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.19482023423146808, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.46755793143523355, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.19355919558818033, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3931759629568022, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.09417456496733598, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.09417456496733598, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.07094072500797352, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3513533312402496, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.23104354771619826, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.40385922879070485, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3633072011801384, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3592209878136327, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.5721408824958313, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3272043176965996, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.49540621006596375, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.3322425567593946, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.505302238370584, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.24002944603900755, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.42818698139212963, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.14662361810887722, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3944286703083527, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.26134221086624515, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.25501149596911343, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "bleu", "score": 0.18038473571185787, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "translation_to", "metric": "chrf", "score": 0.3719715144126504, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.2044743996680912, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.5296253104099969, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.09990095999535835, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.43541588074965143, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1401169793122292, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4782044537286589, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.08807590307622687, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3086025862359103, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3472562426730641, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11696299829645894, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.41815951692436326, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.16743424359150172, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.43311618815403874, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3473759201958039, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3434479962854036, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3943889049582298, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.13754878494693165, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.4400994484887776, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.2623022555609652, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.09666926200219352, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.43859358701110374, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.10655498022151058, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.43007147285347036, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.08570827906588853, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.444312684802016, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.11265744222717027, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.39481530246324914, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.1365091799434783, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.39718585567374165, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.34302997554484677, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.30152990419466674, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "translation_to", "metric": "chrf", "score": 0.3404467436981749, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1689554748507331, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.48752020586891187, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.09863022371664866, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4410680148316049, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.1059024181148723, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.41871695290011, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11117895489854909, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4609024218314948, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11871704290088221, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4586403617409107, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.11481934989482791, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.47478753279668967, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2089685256289425, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5333424925429209, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.46777164721381115, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.15744827002744996, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5597535178949913, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.3906806785529241, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.37503463106800017, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.26125230144349915, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2789924975655291, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.5437335609503513, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.2764393753270045, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.521430018161165, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.21521325160060412, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.549817688316955, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.18948552254902223, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.488827004785696, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.17592391261425677, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.46351362131094864, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0878497559398328, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4566528137749558, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.009020025336134992, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "translation_to", "metric": "chrf", "score": 0.4228408462744233, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.16157821959747307, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5255622543684244, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.15748430756119847, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.530020236187551, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.15089318423122547, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.47428317866010966, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.14391777351450838, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.452101140887801, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.14888606314762867, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.49729350751634693, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.14326513489612383, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4797608004637253, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1296922311601412, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.44753695206116967, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.25815489731794905, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4911644025320733, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.149290338098292, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.47670219817575576, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.46746502686613134, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.10362222834266982, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.2553804995442199, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5077415230970365, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.16531071130846114, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4890742061712915, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1768738680104602, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.5306318459311525, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.14326513489612383, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4846286435143049, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.14326513489612383, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4878418865274075, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.42723061275235275, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.4315166819282004, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "bleu", "score": 0.1428943539626028, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "translation_to", "metric": "chrf", "score": 0.3929455911139461, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.14473479197868241, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4413634590503217, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1842259592735289, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4512010919409926, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2686541301611512, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.48130750228636077, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.14912638561111452, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.39836399000486794, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.20742086615316124, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.49878576838033467, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.12154039608017253, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.41841928964590686, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.15415302247076879, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4123343961300446, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.07756347368634367, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.41174180414190475, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.05358172355226594, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.32818360721376694, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.05900686222697278, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.30171628687493407, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.10650846311095664, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.34263663427911273, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.051646114372149526, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.3047911045736194, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.1299080632357416, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.42087503139452254, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.16733849005024246, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4752813131701307, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.2800051945520251, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.5002082179686791, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.06583464674277996, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4505447671196048, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.17461391742177654, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.42828976335277197, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.09665694287589056, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4197271807950379, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.11578004334848788, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.4640603998690919, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "bleu", "score": 0.06312139294970891, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "translation_to", "metric": "chrf", "score": 0.33724247478267805, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4566114002517467, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.21245026220526622, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5450614695192502, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.23534125777852055, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5178557103050311, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.17312100511353637, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5402176694286381, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.46657292439622594, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20587673103743992, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4757245820906668, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.18087140599571747, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4377272235852682, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.25254176612339824, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.29650451982117443, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.46978147835505735, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.17882068596625036, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5408595600390174, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.46096224066661245, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.20587673103743992, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5260086668248203, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.33325351494406774, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5948182731714917, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.28478979354294687, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.6101591430933082, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.4978503856882466, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.5116515364507819, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.14170261452878116, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.43601861264243175, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.009816976525892437, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "translation_to", "metric": "chrf", "score": 0.39847493267603823, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5049599536473849, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.464305874546181, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5141921869849101, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.19363268497489844, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5704206116375886, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5154606393377016, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.4757656003147759, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5469867443567507, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.22000458484755875, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6138504491885896, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.22000458484755875, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6138504491885896, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.40836418341872194, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.13237645860785527, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.44855614870199234, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.2399509189374762, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.23005567239800093, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5929496962654774, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.21980503399839907, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5614733290167098, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1820057458455135, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5620165305042889, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.17377208785560805, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5789527486073971, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.1761368775330164, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.6050330397163678, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.5589534921007193, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.38966035735880794, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "bleu", "score": 0.3272263309043194, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "translation_to", "metric": "chrf", "score": 0.62085012281251, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.24468026894076475, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2749771763892432, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.24399387658656807, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.3044305895074006, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2005610750993972, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2780404941957844, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.2694630167370006, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.29184952402062775, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1651529607540041, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1596886882102109, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18180630412228768, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.18034760660633942, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20587735759782932, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18120506204127576, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.18120506204127576, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.14637016199691527, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20329087523399839, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.18842975899221734, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.17075840357973465, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.1740044679403827, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.21605512928343784, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.09165698799845141, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.14434599942615042, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.1524760851870573, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.20099656832951143, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.16757404945398316, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.08361504479780595, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "bleu", "score": 0.14745425511282265, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "translation_to", "metric": "chrf", "score": 0.2554284370352702, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24977763651196191, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.21237639792675794, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.20719152387981773, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.017009689511280856, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.16261583096444793, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2819800492878427, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.1925903910576669, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3671206201699281, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3147902135663803, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2726119137509564, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3161459451670598, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.24244700373036193, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2655680598205705, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2291992284121387, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.21972046355478686, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.31901376980971496, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.31793981684013795, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.2163965995950386, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3162880684107879, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.19276213214427151, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.35422146249879416, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.3738879430968546, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2901450731950559, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.2702695112247082, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "translation_to", "metric": "chrf", "score": 0.22144725090715137, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.28494569863631247, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5314415165747192, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.23269544971552114, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.49749977919083926, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.30764071640662, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.6086887537276772, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.27197512669320856, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5796304580865379, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2560035504808655, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5191300553291102, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2755198905868496, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.53562544881003, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2693653652960018, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5351323891749961, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.28048057329781156, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5173444818125783, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.28048057329781156, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5173444818125783, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.16351916864221824, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.48048823975265614, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2652698379999432, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5353598122519497, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.26651453693882154, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5171512452165166, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.18374033535449952, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.49913992421569536, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2435306776669555, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5166317384168408, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.2294197978519848, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.5102280023573198, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.453447647053287, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4578627549446598, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.19991159172412357, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.511242030236653, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4166251963329014, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "bleu", "score": 0.1741974301903178, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "translation_to", "metric": "chrf", "score": 0.4671523918556039, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3780253819893537, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6691463628105327, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2764824153808333, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.669057962133461, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.3202552754791998, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6434556886263748, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.25603152270914875, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5814754099825138, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2897057417455179, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7234741868658244, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.25526757194809524, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6364430511716954, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2503202840132539, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6628587960881935, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.24053590568750352, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6655821853703773, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2778012827037069, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6711394082886347, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.21629919102620548, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6724473560651265, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.09485180281084839, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.529779760886638, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.19994245408068972, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.46449853381454226, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7639212953985626, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.4646770361393315, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7875365172767899, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.19875798613873752, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6616311958065841, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2454606700587796, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6558538403486112, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.2446000556262557, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.7189156627247651, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.6314478474842457, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.39353544541599106, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "bleu", "score": 0.10301175303708132, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "translation_to", "metric": "chrf", "score": 0.5376516921096433, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.2991476612258654, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3082702687589522, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.31985901752714363, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3093019888260462, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.38122846504266117, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.28289355963456897, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5240089168343677, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.15197630365858814, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3903562094322204, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.17096461637332724, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3692462954812726, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3058932494795886, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.45803166077513013, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2215392629217546, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.41257102906156734, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.332926296884715, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.23697705757746226, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2718193327400847, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4809886758134228, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.236183472854973, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.4962696728269181, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3397501129479015, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5046267909194274, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.3039889130898378, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.5189316341976646, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.2737404369432603, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.44170111004367846, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.09276734202644997, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.34738831385047086, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.038929274966113724, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "translation_to", "metric": "chrf", "score": 0.3715413713289065, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.125959010609916, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4578429795465262, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3002210625771089, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.10836164033218013, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.2822470723835753, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.30837343649807475, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.16285656455323885, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.38593361366316536, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.08092905161582194, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.40325551743862786, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.17677215260187162, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.42492794367017145, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.31671366337624424, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.25561861397357827, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3066033339868866, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.13670948742268121, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4671925185138795, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.26302325128893417, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.14677278920264347, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.43976708356683103, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.155064927647868, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4475601468947218, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.11572453857976596, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.40350265317086687, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.08609583710384033, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.393787114023589, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.15179857311923614, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.4250156741030636, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.3082198822374831, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.09663983962924942, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "translation_to", "metric": "chrf", "score": 0.28623327813191574, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2686036309072948, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.46796278650100787, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.32114886466116627, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4290130719589314, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.31745588252583107, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.47247928950031065, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.19602407208403763, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3632643493569709, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.31282819180907734, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4675168560541054, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2830521145956212, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4573087432916607, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.22312700803550112, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.41892404547996925, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.20687905897572376, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.362340397723073, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.20687905897572376, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.362340397723073, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.22579912926222612, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3783017116228253, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.32978577921952357, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.42924039608828407, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.14088570267002404, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.3918583817524295, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.3766280281182921, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.561875298764404, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.30926866193743463, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.4734674396049645, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.32379826522537186, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.46258247655884976, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.009198656648134795, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.25957913590023596, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.38356760326816786, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.2430631876672867, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.43715989625290264, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.0180364018094266, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "bleu", "score": 0.17628695321990814, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "translation_to", "metric": "chrf", "score": 0.35674625496754503, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3021887988636079, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.45419878739503283, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.23552484042758592, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4709821983218137, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.27344034184005456, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4592757626540918, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.24521459631436066, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.39838009260057416, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.38474707938945013, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5248793758647762, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.23416315942114563, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4208857451138015, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.38791398909746805, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5307069804730096, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.11525474107629258, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.3599175708579159, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.31490883229126904, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.19107718673008198, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4125999494584315, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.34524014843941836, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4895068008032555, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.30994419975665016, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4742646380437834, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.5050428988316858, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.6493635959645938, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.4052322980796165, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.49611847082895705, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3328216606045846, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.4941913602504158, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.053879020811737684, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.38021491541756264, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.31392132264048933, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5754896830224385, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.12453127610933407, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.29863174206979526, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.007211634308109934, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "bleu", "score": 0.3243463643565424, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "translation_to", "metric": "chrf", "score": 0.5301315752666177, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.26012602101891624, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5371799694530636, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.14137375964454066, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4881276325562942, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2524400150751196, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.543218311413834, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1680217411909958, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.476749806940524, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.21986501688175145, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5475496671985627, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.18643403650822063, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.47409410383361306, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.15942530661337126, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5151997420421937, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.1551207146087495, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.45222225168463764, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.07562263205281951, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.40405285180350065, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.11247951467712404, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49181415463176537, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.26037258624452736, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5454235944725728, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.07343660663917347, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.3787234084201135, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.2921802715934955, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5926371897941235, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.11125382292406938, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5333694859964047, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.16669278390769504, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49159200223893573, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.41163971744852484, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.6347999526262019, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.3447572227473206, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.5387838115437739, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.4062756549837031, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.04596396358288162, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "bleu", "score": 0.17188988271346264, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "translation_to", "metric": "chrf", "score": 0.49227421818586253, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.05156674665890638, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.36698218242626135, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3430290995002961, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.21039621982729317, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3552217341881303, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.29842536574876644, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3490672284963974, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3280456612129034, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.24230069025465048, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.26455714412627024, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.13029936621144683, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.03935386961535685, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2024319322301778, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.11865659492276644, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.43729335450310336, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.07043397949482622, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3852802461214156, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.3227864720021685, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.14627961137626996, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.44627375475551206, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.15387660309188697, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.4518012668858871, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.32862413291299897, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.008721090647871285, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "translation_to", "metric": "chrf", "score": 0.2647246444953521, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.09952498083578393, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3978595245805609, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.10916808066739564, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.43671495255219495, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.10681900656181822, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4311441166019649, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3941055692915637, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.09015951516022348, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.41181252304348637, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1191908679309468, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.45187698687012057, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.10615684540251687, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.460046617317305, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.23054527938920757, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.49607909097851804, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.23054527938920757, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4915475454360348, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.13869428765868777, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.46453154080273173, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.1001225426710981, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.40793765705272267, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3829530312593843, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.228441262407929, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.49042651481296606, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.09051954027868377, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.3959277285416738, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.139731584961703, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.42457915173356314, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0969377041969594, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4325087280742601, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.13675976358974223, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.4986242378041087, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.37656227734611086, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "bleu", "score": 0.12588329541191326, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "translation_to", "metric": "chrf", "score": 0.41955518796523705, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.38459672847260074, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.41318454544592675, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3093723160200868, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.3100065568321291, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.47847792583530074, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.07243671671799473, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.39798076169845714, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.413922696186207, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.24716364461082166, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.23820815591418562, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.07498532429953313, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.10846480297768277, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.13086094852026312, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.10533861301133443, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.48564427576794694, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.1670515635012818, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.5251495423402189, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.40063869758193577, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.4223466541571402, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.43551167119135525, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.2548887818537811, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.022883128970738017, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "translation_to", "metric": "chrf", "score": 0.339150270719077, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.14073835588074438, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3186851468537677, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.11092528636668526, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.31604383600836816, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3032188091357597, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.07647695577791483, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.2986901902965963, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.2061578366200879, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.37101078385857167, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.11823053204772466, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.33614010685052986, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.13839209880933745, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.35315147740153213, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.10306540752539145, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3271343056196344, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.10306540752539145, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3271343056196344, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.079343898106884, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.11055607910487246, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3203685139724149, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.13862954544342151, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.10447015481416681, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3834682647143798, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.1570432711803692, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3293030041429665, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.24985540866207695, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.43357023350146434, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.33987749185852145, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.09763088860404724, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.3488516919947926, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.2863678077311179, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.17460041508427898, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "bleu", "score": 0.0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "translation_to", "metric": "chrf", "score": 0.28744629692241225, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ur", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "mr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "jv", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ta", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "yue", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "arz", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "gu", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "th", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "kn", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ml", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "or", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sd", "task": "classification", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 0 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 1 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 1 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 2 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 2 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 3 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 3 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 4 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 5 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 5 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 6 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 6 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 7 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 7 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 8 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 8 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "en", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "zh", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "hi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "es", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ar", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "bn", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pt", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ru", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "sw", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "id", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "de", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ja", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "te", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "vi", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fa", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "tr", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ko", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "it", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "fil", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "pl", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-4-maverick", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3.1-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "meta-llama/llama-3-70b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "openai/gpt-4.1-nano", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-4o-mini", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo-0613", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "openai/gpt-3.5-turbo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-small-3.1-24b-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "mistralai/mistral-saba", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "mistralai/mistral-nemo", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.5-flash-preview", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "google/gemini-2.0-flash-lite-001", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 1, "sentence_nr": 9 }, { "model": "google/gemma-3-27b-it", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat-v3-0324", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "deepseek/deepseek-chat", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "microsoft/phi-4", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "microsoft/phi-4-multimodal-instruct", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 }, { "model": "amazon/nova-micro-v1", "bcp_47": "ha", "task": "mmlu", "metric": "accuracy", "score": 0, "sentence_nr": 9 } ] }