[ { "model":"amazon\/nova-micro-v1", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2294045445 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.4952691669 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3288016428 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5463705477 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2027365964 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4429221375 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.2592014549 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.4502390132 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2486422994 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5046441311 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.390442231 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6258445826 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4829593782 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6670785718 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5654501085 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7810071072 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2334919219 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.488808171 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3534859166 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5837022928 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2616894756 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5082668021 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4039820936 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.5963334297 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3412962275 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5789604921 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3866780476 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.60404499 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1741677254 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4469342589 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.1716570673 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.5608938423 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.4 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2197709837 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4784848367 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.3426239655 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4822747548 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2192585886 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4527368673 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.1076519805 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.4493011434 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.1387332093 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.4231622054 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.1326285083 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.3320956129 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3548435009 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6046727327 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3341282505 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.4931240563 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2534618489 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4757478619 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4150555406 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.632650236 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.173300895 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4267275321 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.2934481188 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5432096638 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.203432711 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.4661592161 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.260138004 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5610336232 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3031235597 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.537458124 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3112392832 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5195600347 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2338522454 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4761317098 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.1016530484 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.3475324071 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.122224664 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.3790772862 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.1919159066 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.4399907204 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1734447333 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4737881775 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2855931625 }, { "model":"amazon\/nova-micro-v1", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3243323503 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2660357996 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5489237487 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3431691167 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5659025601 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2999810338 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5315905896 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3568113924 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5379558638 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3410327538 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5702449417 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4621824412 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6644677733 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5530727537 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.7075859327 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6368037655 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8170495194 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3558328881 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5816613686 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3018683161 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5862734644 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3482763208 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5982327963 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.452269216 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6590312745 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3747394322 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6079633657 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.4420465241 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6372857982 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3120299438 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5421647326 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3139800299 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6305869448 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2121435327 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5165098934 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.3965805608 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.5197322727 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2594796679 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4780086047 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.3009966401 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5761529867 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2536168105 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5193737639 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2743904396 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4918283752 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4307107958 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6547934264 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3789232965 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5490387026 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3491027097 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5771246685 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.3737440632 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6547073078 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2584319121 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5177022275 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.371218137 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5948906549 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2583542451 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5157482031 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.3458513734 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.634706105 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3887890595 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.6100201392 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3146346509 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5476489231 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2324983634 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.497221173 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2976387517 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4761547661 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.3027505857 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5506378818 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3708866541 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5846851624 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2377253988 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5405656214 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2660263348 }, { "model":"deepseek\/deepseek-chat", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3459946232 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2993048546 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5651988199 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3853695566 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.602672086 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2798537803 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5394779979 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3719179468 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.539682577 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3207762021 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5555389401 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4227752207 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6601015066 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5548034204 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.7071106777 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6432470265 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8278285651 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3223436235 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5379000389 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3061941236 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5918382188 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3297556296 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5925809306 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4619761505 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6734036273 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3412169553 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.598919602 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3937102354 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6229439454 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3020610187 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5462026627 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.299038365 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.625735911 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1875636541 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5136106256 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.3333377273 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4709407515 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2789250445 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.52614288 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2580648249 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.574708573 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2487969868 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.518708582 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2238578938 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4748109447 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3823229705 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6453681393 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3548387061 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5492435889 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3091555064 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5528775735 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.3860807525 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6710753294 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2464304597 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5343201712 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3592456339 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5816925415 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2438930348 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5213646779 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.2864351463 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6249321785 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3464968589 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5970733128 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2948086539 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5417485172 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2290327476 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5229250115 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.3122409611 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4921734247 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2150236607 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4970978512 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3603191861 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5938509481 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2350235637 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.528086246 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2524231151 }, { "model":"deepseek\/deepseek-chat-v3-0324", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3456705882 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2238237549 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.4534366926 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.2689055687 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.4149416248 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.2 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2443635406 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4676159664 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.2223182846 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.3685961254 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2633055293 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.451378667 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.2576565152 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.3874723625 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.3974650186 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.5373829936 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5868227988 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7574063883 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2163623393 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.4705179867 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.2458237388 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.426538099 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3182982487 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5389072956 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.47314841 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6884710951 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.2 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.2684001499 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.416230929 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.2827365983 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5128198247 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.2 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.223787985 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.485186041 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3571004344 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6398491182 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.2 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1711796281 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4108641598 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2194500975 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.3589526769 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.1994883012 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.3942042616 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2570478693 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5215463463 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.1828389227 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.3179756072 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2129586558 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4314516197 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.252814761 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.4131775231 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2671823746 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.3966391033 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2348823133 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4500923911 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4182790857 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.649967582 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.1839314203 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4234191674 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3489148579 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5567945257 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2041105012 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.3657796945 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.3130978532 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5950962977 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.1200373123 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.3196364935 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.1814754432 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.3157059838 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.181272453 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.386776605 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2603415771 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4241396601 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.1705385375 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.3747437419 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.257036702 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.4598854693 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.1 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2137844239 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5028557922 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.3129908127 }, { "model":"deepseek\/deepseek-r1", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3710290799 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.3412745465 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5826925715 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.390058702 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.597901367 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2988263355 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5680625724 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3895386095 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5693830083 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.4245142301 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.6390046108 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4937713215 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6856946146 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5700014681 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.7211557733 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6711231356 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8279616884 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3344072959 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5751886204 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3905772718 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6166676981 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3411643102 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5823324237 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.549646027 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7334440232 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.4434404142 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6607832834 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.4308263411 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6353494719 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3626330278 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5869542517 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.4368014195 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6964617832 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.3331002174 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.579659503 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.336969824 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4913494739 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3700621486 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5837249923 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.3088767184 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5884562937 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.3338185652 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5787491818 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2806196555 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4516145469 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4372599799 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.658993109 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4174871385 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5931595705 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3198419121 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.578067895 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.5056809967 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6966172136 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2839962776 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5461994333 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.4589390255 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.6469214364 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.4043048116 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5944297519 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.499303533 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.7212747243 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.4243816819 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.6336752528 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3644641049 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5789291672 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.31244285 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5630479496 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2911146353 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4826415387 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.3436662566 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.59026429 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.447007323 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6624838094 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.3075560511 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5721434339 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.3628421643 }, { "model":"google\/gemini-2.0-flash-001", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3921364269 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2723646085 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.523730035 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3878873306 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.592059186 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2672489266 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4952818431 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3639249804 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5538942616 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3382313883 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5705047774 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.5354923841 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.7125417889 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4617498931 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6321211549 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5951204739 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7613397345 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3547349164 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5728186386 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3576086442 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6061019948 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2978444639 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5625976718 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5244850062 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7081676298 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.4286739426 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6359453866 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.4344801023 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6474630132 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3126497326 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5733116043 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3882402101 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6624914478 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.289402493 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5452343766 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1879084772 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.3787664659 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3561823456 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5619277442 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2609272138 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5344454302 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2906692433 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5058194876 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2450137243 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4736891146 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3792889323 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6001893022 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4267930078 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.583867208 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3275326122 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5672682921 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4390630519 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6588223005 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.266439807 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5101737799 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.4085478092 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5658655698 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2763965367 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.520411275 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.4350912598 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6853284539 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3528600199 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5850279702 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3231474889 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5470305035 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2859928961 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5295533045 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.3010091175 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.493353195 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.3170290484 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5491010642 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.4032471641 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6394566771 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2557280993 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5212143675 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2610248692 }, { "model":"google\/gemini-2.0-flash-lite-001", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.314329989 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.3462011916 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5813984303 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.4319399394 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.6269389132 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.3332105938 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5788748413 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3925309816 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5671456285 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.4080538745 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.6278026445 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4940498755 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6915113583 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5780592594 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.727062887 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.725042796 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.868453404 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3228577771 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5691176688 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.4211069488 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6329026504 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3683003934 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5961800274 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5899042948 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7506595836 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.4661333335 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6599650679 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.4319599559 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6493733048 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3507436052 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5856872774 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.387557065 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6730969345 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.3590987818 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5958999814 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.4151803591 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.5319028037 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3793672083 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.6054760312 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.3161702144 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5956895972 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2888720948 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5411662197 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2820351359 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.5017455952 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4833653569 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6877252787 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4959043786 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.631939007 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.4185968559 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.6194298291 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.5066913819 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.7045563325 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2835606416 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5525332546 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.5294387768 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.6814959444 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.4452506057 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.6299322033 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.4773237879 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6983325706 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.4838983303 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.6878651593 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.4225689448 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.6171822766 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.3194163699 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5758075077 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2609063103 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4351160146 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.4227968054 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.6326522416 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.4693432911 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6659480306 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2632355471 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5527183044 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.3128970722 }, { "model":"google\/gemini-2.5-flash-preview", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3699956681 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.3509446122 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5872861306 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.4369226272 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.6357392299 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2928560114 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5373877759 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.371713483 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5467648432 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3827187056 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.6092943987 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.5181328066 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6981190119 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5942868447 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.7298379077 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.7309888475 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8534239972 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3497891701 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5889817614 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.395885417 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6273835234 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3737227872 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.6039484183 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5555743798 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7229519037 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.4387215588 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6443095169 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.4255607348 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6457270128 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3789722313 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5973074889 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.406320567 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6828299565 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.3423388267 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5884893314 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.3740472584 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4832664839 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3540174328 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5513315973 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.329885986 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5805485408 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.3055522766 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5435968357 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.257460039 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4845716024 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4182659606 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6696655487 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4665320226 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.6280330147 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3485890022 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.574915747 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4760104707 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6891420805 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2893557086 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5514512546 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.4910352633 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.6636379715 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.397583037 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.6014699575 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.4540021563 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.7002830052 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.4025505277 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.6339036498 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.4166086163 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.6171953291 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.3212777323 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5735084601 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.3027958989 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4912965943 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.3471784526 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5719753053 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.4601231177 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6644848789 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.4 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2989639846 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5646599732 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2915310914 }, { "model":"google\/gemini-2.5-flash-preview-05-20", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3358004159 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2747843596 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5519960681 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.2863967069 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5318173199 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.271237739 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5173954387 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3067537945 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5194482945 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3189602129 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5548503533 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.5229096392 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.7023434262 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.3889146477 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.628092835 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.4660772497 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7280386297 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3593767686 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5668073679 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3662275621 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6102640711 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3180384008 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5571267732 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5778354146 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7490356238 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3722751955 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6207213131 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3378499277 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.554090013 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3583744222 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5732194975 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3364664006 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6438910651 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2581140706 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5395853617 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.3298839393 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4471547552 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3177915441 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5387853038 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2549228547 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5322440265 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2370074805 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.4804215458 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2399769139 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4726429935 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4180718844 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6426219278 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3938693136 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5573992167 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3537745123 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5904429929 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4588664196 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6844540285 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2449777422 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5268764903 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3789708434 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5790333031 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.3005035588 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5210660172 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.3401968092 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6217197146 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3330093484 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5694168709 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.257812168 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5167002436 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.322448107 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5887654616 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2148139783 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4226865444 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2745000434 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5206422805 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.4261790941 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6358462464 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2201641871 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5051068628 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2508351517 }, { "model":"google\/gemini-flash-1.5", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3110461024 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.260683336 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5383651277 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.2962406565 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5190026627 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2183929994 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4877941086 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.2700916391 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5150577414 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3440655166 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.563902418 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4305522274 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6477508732 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4113463435 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6260248317 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5310035709 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7595845064 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3031284355 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5241309352 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3289699508 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5811203167 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3349110908 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.564806297 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4574014191 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6626552528 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3184042229 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5712698408 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3659029431 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5796195236 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.2301748885 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4682741896 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3346592082 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6514874668 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2664966821 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5386982677 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2651365589 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.409095006 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2326358655 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4815897231 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2187928356 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.4896578943 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2256246926 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.4703189943 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2254492518 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.447826525 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3706063992 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6167676482 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4234596823 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5629443923 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2971403532 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5321068893 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4364286549 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6509885745 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2300270544 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4839384065 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.4236492288 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.6116207052 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2501435914 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5088299265 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.262372343 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5806899403 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3568851036 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5825326367 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3112091725 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5431414206 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2402951661 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5033005385 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2302239803 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4066956434 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2537752957 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5073147534 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3583753747 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6253917282 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.249810194 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5151255506 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.1854861198 }, { "model":"google\/gemini-flash-1.5-8b", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.2463326959 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2891206499 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5438550217 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3184721364 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5483731849 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2907230812 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5148223626 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3473636391 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5442574441 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3577876868 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5943423055 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.5344280565 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.7084649844 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.452427177 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6525566656 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5467976399 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7780833183 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3554331718 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5997743406 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3847830842 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6191109047 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2846092378 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5655970541 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5192984544 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7020040834 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3520691191 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6035990708 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3987037224 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6195037668 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3377417704 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5674360496 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3534620252 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6680177029 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2481856237 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5180749152 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.242508046 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4046420215 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3019627022 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5133980923 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2316517545 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5189963647 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.3395095603 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5877742809 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2222923122 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4572688692 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4164890636 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6375470445 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4166823661 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.575314128 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.340245547 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5681284927 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4702737577 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6903236014 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2862936285 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5264436928 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.4800957551 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.6618495803 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.268709657 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5306834056 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.3395981599 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6130756934 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.2 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.2787922254 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5420797212 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.259866454 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.48543634 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2595582459 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5043992681 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2142625601 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.429749938 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2279880384 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4835933272 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3478085621 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5968604742 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1900086584 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4895930442 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2395565562 }, { "model":"google\/gemma-3-27b-it", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3237759485 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.0837265107 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.3012065838 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.1120670716 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.2771296913 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.4 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.021858254 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.2327499821 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.0253088472 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.1918662187 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.1784955678 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.4008799371 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.1782663616 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.4070825897 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.2797104835 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.4601471921 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.3392404298 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.5518674496 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.1682956348 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.3705606944 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.1595479626 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.4040956812 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.1362099506 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.4039646029 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.2151785904 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.4309035319 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.6 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.2 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.1658307051 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.3676480008 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.1711676323 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.360371738 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1399603895 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.3604113675 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.1312450274 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.3988827234 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.1 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1222242366 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.3415186168 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1607198845 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.2706371796 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.6 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.0550016522 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.2468917982 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.017690474 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.2536001746 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.4 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.0411296617 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.2442292695 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.0482775033 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.2211003771 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.2292007848 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.3716655897 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2126702079 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.3248815955 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.1013445398 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.3063125264 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.2231857524 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.4401829864 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.1005466956 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.3356518748 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.1363185356 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.3769111636 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.0510060878 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.2132741272 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.0089146903 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.2314109768 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.2 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.1 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.1096331511 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.2888090685 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.1206114883 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.2597106436 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.0891185343 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.281793335 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.0799576366 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.2661903898 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.2 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.1389065496 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.3708687542 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.1661316612 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.354399593 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1133138775 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.3754190494 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.1672636279 }, { "model":"gryphe\/mythomax-l2-13b", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.232325354 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2609114367 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5167379854 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.1932802581 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.4648835751 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.1938367121 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4674774016 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.2073541352 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.4438396219 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2685056004 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.506818165 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.3801657831 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6056477234 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.2216031518 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.4429472312 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.3322887566 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.5824514758 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.1640783778 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.434749516 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3126220052 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6038883227 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2261588318 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.4944996319 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4626001556 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6614963779 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3316295853 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5594083443 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3598049012 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5828568956 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.2236143729 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4912948296 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.2910526755 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6005590773 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2131020144 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4845704057 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1446650781 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.2292145443 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.1840709267 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4042090141 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.1902389614 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.4796942089 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2152417217 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.4578207034 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.1654073391 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.3941079443 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.1891048622 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.4238091524 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2086330089 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.364326938 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2256776552 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4793769886 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.3320822339 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6132478102 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.1730354472 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.454951133 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3073459183 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.554890569 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.1798653655 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.4290347271 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.1709237193 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.522080463 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.2507091988 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5067409185 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2998213366 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5112516267 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.194871957 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4838690709 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.1908512613 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.3855814375 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2003733128 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4613442635 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3326058501 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5496097026 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1869648376 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4664675781 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.1696786467 }, { "model":"meta-llama\/llama-3-70b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.2325846099 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2766513185 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5528193738 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3371708551 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5607841978 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2623045124 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.512895511 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3328087961 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5013967236 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3059254014 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5403551155 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4588037752 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6692431614 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5486108614 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6873139374 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.691450825 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8407064328 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3021494986 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5604145602 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3865320679 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6126903448 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2924853239 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5462367408 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4963618411 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.682573515 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3914590212 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6128431348 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.4189427376 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6262550579 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.290274553 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5143960108 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3789023659 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6751523776 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.3306727326 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5648258387 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.262512317 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4036795798 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2593989014 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4825732152 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2177203514 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.452576603 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2987546297 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.526361525 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.1515083487 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4332812085 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4479091606 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6272058507 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4155919737 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5685427433 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3183331223 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5559144449 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4500659682 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6761551234 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2051262499 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4837372958 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3699194641 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5770913921 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2983575506 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5283269577 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.3087303367 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6028401745 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.357367421 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5659157865 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3515649071 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5645706042 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2584265792 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5020697076 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2624388601 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4452300688 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2872551102 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5360250569 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3575088107 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5879974234 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2619931658 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5251502482 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2725475868 }, { "model":"meta-llama\/llama-3.1-70b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3148065512 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2166642565 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.4531623464 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.2433592841 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.3890038008 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.1749870589 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.3959743603 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.1992458221 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.3995820747 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2301502689 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.4644650793 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.2921772734 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.4951314188 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4124666467 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.582315662 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5519762012 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7446058172 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2337331881 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.4523774022 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.2045157252 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.4389018917 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2381890937 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.4806457757 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.3213357404 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.5096591733 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.2951777856 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5193991656 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.332068694 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5232846835 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1717243204 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4178336488 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.1865357446 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.429444403 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1933631076 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4686346426 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1629637627 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.265082494 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.0726508623 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.3051851212 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.1282743245 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.3321469572 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.144541816 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.3648764501 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.1047482644 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.2965277611 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3595710948 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.539538196 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3110476538 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.4964416902 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2073899393 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4691838054 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.1956364634 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.3100521945 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.1671614266 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4422244829 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.1893614933 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.4605763082 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.153544279 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.381670314 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.0470329064 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.3516233998 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.2177874056 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.4228885108 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2215396728 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.4514044695 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.142024307 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.3925303581 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.13811776 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.3521086255 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.1850447544 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4328029287 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.2262846976 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.3523271738 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2115579648 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4634573062 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.1903215556 }, { "model":"meta-llama\/llama-3.1-8b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.2429625775 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.0534412445 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.1423750168 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.0522677244 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.1317238701 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.0061046998 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.048395385 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.1624192131 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.1 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.0365328036 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.1594198405 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.089863703 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.2290725718 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.1186358374 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.2861009841 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.0659782167 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.1219080159 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.0197183104 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.1858500787 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.1372446539 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.1970334371 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.0225723033 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.2128372612 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.0900337367 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.2030113676 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.1 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.1275394125 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.2249822055 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.1164104087 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.2255759794 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.0396919548 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.193498077 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.0463130015 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.147263979 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.0196332917 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.0615297483 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.002077843 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.0228028425 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.0192847454 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.1432000045 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.0179600462 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.1308378956 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.0103335448 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.0394434629 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.0093410183 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.0758287765 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.2072883352 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.2238489904 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2192906863 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.330676254 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.0506856305 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.2502940387 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.0801303171 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.1635269784 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.050859162 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.2002283949 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.0199756762 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.1055944134 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.001996605 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.1999016804 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.0453589274 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.1405820992 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.1115247653 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.1296059134 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.1480453761 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.2690624141 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.0114376329 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.0233475148 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.0385720696 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.1423687352 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.0697220351 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.1874677848 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.135086862 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.2446182636 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.1 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.0190942897 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.1108498114 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.0 }, { "model":"meta-llama\/llama-3.2-1b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.0294450289 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2997360932 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.552448295 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.2837522278 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5150814494 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2646772038 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5157826791 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.331255344 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5093924414 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3129672706 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5456543979 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4852409005 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6908376394 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5510215557 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6909834226 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6679215449 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.823262947 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3139331841 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5454623234 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3561290923 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.599796306 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.4 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2963449909 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5544997379 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5091700689 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.690320784 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.385731086 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6034244629 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.357812342 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5894721809 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.3143630083 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5621460006 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3372718385 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6543894215 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.284322765 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5304019177 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2212745751 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.355950114 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2779520489 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5022141687 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2476437073 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.4805413308 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.3224419544 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5606155155 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.1663847917 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4383662593 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4519562833 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6328740374 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3918546765 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.551810658 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3065957195 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5567333989 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4450524918 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6712742861 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2184907643 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4824691404 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3406091079 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5689518318 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2373393477 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5017230165 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.2334583695 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5603415221 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3767393472 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5870286691 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3415510311 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5592933672 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.252958993 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5053979802 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2339821201 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.425306622 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2721498467 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5200799335 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3613736416 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5866656133 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2259180607 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5258178103 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2474954475 }, { "model":"meta-llama\/llama-3.3-70b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.2841722148 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.3288891576 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.560493221 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3370289388 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5616376735 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.3130233588 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5569163893 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3322667951 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5140240989 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.386239845 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.6110300223 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4508475568 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6653203029 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5649266234 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.7240609445 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6160790992 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8133281991 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.3152773331 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5548531112 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3335962816 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5859881472 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.3174175523 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5682518332 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5173973527 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.7056428374 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3796955055 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6056742688 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.382370623 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5922578575 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.2523550022 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5458277736 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3774331947 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6486159416 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.3130983776 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.5536124921 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.3266051607 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4444671407 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.3146151088 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5434123174 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.3068652176 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5696595268 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.3125095049 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5535296132 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2275791183 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4569915545 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4246522462 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6364852561 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.439726575 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5806732389 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3451568022 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5845365036 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4582156105 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6491023878 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2567420946 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5061211552 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.4025875747 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.6083538055 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.3425500041 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.5680420054 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.2980763573 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5924685945 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3462186566 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.6055817314 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3822149946 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5783618359 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.253549974 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.5235064606 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2484556869 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.429442787 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2670924013 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5198891912 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3597766713 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.6081806669 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2703289724 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.5473102513 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.317769874 }, { "model":"meta-llama\/llama-4-maverick", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3676906362 }, { "model":"microsoft\/phi-4", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.1548779531 }, { "model":"microsoft\/phi-4", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.3887963415 }, { "model":"microsoft\/phi-4", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.268706305 }, { "model":"microsoft\/phi-4", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.4959259833 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.095240952 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.3840548344 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.1876367188 }, { "model":"microsoft\/phi-4", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.4310988737 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2546126219 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.4840060449 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.3171866034 }, { "model":"microsoft\/phi-4", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.5752285995 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.3642023499 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.5697992815 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.4959810553 }, { "model":"microsoft\/phi-4", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7232313255 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.1732534835 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.4434970776 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3605235101 }, { "model":"microsoft\/phi-4", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5849733787 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.1763652726 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.4428784232 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.3772793055 }, { "model":"microsoft\/phi-4", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.5820724576 }, { "model":"microsoft\/phi-4", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.2788689746 }, { "model":"microsoft\/phi-4", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5417455941 }, { "model":"microsoft\/phi-4", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.2369610218 }, { "model":"microsoft\/phi-4", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.3765795877 }, { "model":"microsoft\/phi-4", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.0855471394 }, { "model":"microsoft\/phi-4", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.3720740561 }, { "model":"microsoft\/phi-4", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.284365864 }, { "model":"microsoft\/phi-4", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.589202199 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1462066826 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4299215293 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2371087689 }, { "model":"microsoft\/phi-4", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4064089202 }, { "model":"microsoft\/phi-4", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.1102793601 }, { "model":"microsoft\/phi-4", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.3718502317 }, { "model":"microsoft\/phi-4", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.0999035402 }, { "model":"microsoft\/phi-4", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.3664761129 }, { "model":"microsoft\/phi-4", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.1012625471 }, { "model":"microsoft\/phi-4", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.3580813711 }, { "model":"microsoft\/phi-4", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.0891010327 }, { "model":"microsoft\/phi-4", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.3158325956 }, { "model":"microsoft\/phi-4", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3550414512 }, { "model":"microsoft\/phi-4", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.5626107823 }, { "model":"microsoft\/phi-4", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2784963846 }, { "model":"microsoft\/phi-4", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.4121299981 }, { "model":"microsoft\/phi-4", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.1813353123 }, { "model":"microsoft\/phi-4", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4632560004 }, { "model":"microsoft\/phi-4", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.3450201321 }, { "model":"microsoft\/phi-4", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.5827805827 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.164734586 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4400610126 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.2884407046 }, { "model":"microsoft\/phi-4", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5338739518 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.1325294802 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.4051925402 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.1631216823 }, { "model":"microsoft\/phi-4", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.4696161488 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.2374723306 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.4675485501 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2528444882 }, { "model":"microsoft\/phi-4", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.4794045124 }, { "model":"microsoft\/phi-4", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.1155003818 }, { "model":"microsoft\/phi-4", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.3250077925 }, { "model":"microsoft\/phi-4", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.1195513435 }, { "model":"microsoft\/phi-4", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.3158904676 }, { "model":"microsoft\/phi-4", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.1452425625 }, { "model":"microsoft\/phi-4", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.3941195385 }, { "model":"microsoft\/phi-4", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.2680553268 }, { "model":"microsoft\/phi-4", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5055559664 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1516445239 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4517979691 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2058198052 }, { "model":"microsoft\/phi-4", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.2799124898 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.2 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.1428907436 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.3107041775 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.1849770017 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.2932088535 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.0355167863 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.2600874171 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.0323184525 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.1970289791 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.1237340737 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.3601104142 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.1371705946 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.4120757797 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.3548422361 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.460765953 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.4690424472 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.6788013861 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.1169662945 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.3242693179 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.2556403143 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.4583071754 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.0839707225 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.3074010094 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.2478840637 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.4205657928 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.1989310744 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.408792844 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.2107266229 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.3722535388 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1251179936 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.3078536626 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.1049757961 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.338086632 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1170990874 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.3281623219 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1166577127 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.2303280443 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.0192945074 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.2015068169 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.045857499 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.1778848232 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.0250471784 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.2097577846 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.034382114 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.2211758055 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3055395757 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.4480585816 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2165906221 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.3271537328 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.1031395116 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.3223915745 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.1194174782 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.3618255907 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.0826481083 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.2913230821 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.1808682916 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.3815777762 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.3 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.0422003709 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.253591842 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.0280729387 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.1884927612 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.1550101498 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.3623113506 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.1217984824 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.2801870917 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.7 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.096255918 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.2490196736 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.0759551519 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.2765897266 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.1578714698 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.3784433754 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.1713340477 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.3260532752 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.0821079546 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.3164863838 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.1265931852 }, { "model":"microsoft\/phi-4-multimodal-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.1793067232 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.1314009634 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.3827163755 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.0953897712 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.2894343613 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.1016298945 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.2980803254 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.0978160022 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.2190252958 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.1786073211 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.418923403 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.1529904036 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.4257110482 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.3166864072 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.5483508218 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.4404172544 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7231001513 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.1298121807 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.3403579227 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3743863952 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5971283997 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.1078563354 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.3207926618 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.3659011486 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.580998869 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.1271878224 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.3698932868 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.1324625901 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.3233634009 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1489627056 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4172638299 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.2008824981 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.5185852751 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1169165949 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.3638899173 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1330552123 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.2685952079 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.0823011221 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.2825939861 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.0327082346 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.2319054893 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.1016737952 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.3529445259 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.0980137705 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.3076980329 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3158857772 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.5109022919 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.2903521386 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.4758823803 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.1398701241 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.3034565852 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.3460979115 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.5835851988 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.1 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.0947682488 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.3259777135 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.1796274314 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.4360781177 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.2 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.0669163701 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.2784916366 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.0633186191 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.3074668268 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.1471870965 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.3392441061 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2060450795 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.3717773766 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.0522713846 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.3192866676 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.0868686952 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.2859772299 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.0649160569 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.2830042558 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.0350138164 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.2206802597 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.0 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.0992800287 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.324429867 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.09185491 }, { "model":"mistralai\/mistral-nemo", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.1769207611 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.278999196 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5072892325 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.335915232 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5453940527 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2557484343 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4816174974 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.336565743 }, { "model":"mistralai\/mistral-saba", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.500099888 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.33652498 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5394051209 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4124704223 }, { "model":"mistralai\/mistral-saba", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6500309258 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4669071745 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6351301458 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5813419207 }, { "model":"mistralai\/mistral-saba", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8065247071 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.293714449 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.4892518335 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3400529578 }, { "model":"mistralai\/mistral-saba", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6054518089 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2548863763 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5181895957 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4309072933 }, { "model":"mistralai\/mistral-saba", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6122951839 }, { "model":"mistralai\/mistral-saba", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3708164771 }, { "model":"mistralai\/mistral-saba", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5780452995 }, { "model":"mistralai\/mistral-saba", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3889665973 }, { "model":"mistralai\/mistral-saba", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5940361548 }, { "model":"mistralai\/mistral-saba", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.2714445111 }, { "model":"mistralai\/mistral-saba", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5033343062 }, { "model":"mistralai\/mistral-saba", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3367134056 }, { "model":"mistralai\/mistral-saba", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6204206544 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2208745982 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4944838309 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.1755723698 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.3733502483 }, { "model":"mistralai\/mistral-saba", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.1125731148 }, { "model":"mistralai\/mistral-saba", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.2778916971 }, { "model":"mistralai\/mistral-saba", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.0861201622 }, { "model":"mistralai\/mistral-saba", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.3310005151 }, { "model":"mistralai\/mistral-saba", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.3097940645 }, { "model":"mistralai\/mistral-saba", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.5304242832 }, { "model":"mistralai\/mistral-saba", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2168719994 }, { "model":"mistralai\/mistral-saba", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4555868419 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.4077844252 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6076754833 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4459003493 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5840266721 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.264907032 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4939362461 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4563355662 }, { "model":"mistralai\/mistral-saba", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6843169799 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.1955652432 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4654058492 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.2591393679 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.4936043335 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.0845702794 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.2799479817 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.1327606257 }, { "model":"mistralai\/mistral-saba", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.4346855791 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3805998732 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5566308844 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3811390337 }, { "model":"mistralai\/mistral-saba", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5895281984 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2469989894 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4943114536 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2844546137 }, { "model":"mistralai\/mistral-saba", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.477210689 }, { "model":"mistralai\/mistral-saba", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-saba", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2373174322 }, { "model":"mistralai\/mistral-saba", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4521152897 }, { "model":"mistralai\/mistral-saba", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.2962197342 }, { "model":"mistralai\/mistral-saba", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.544285644 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.2391219094 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4993680631 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2546682455 }, { "model":"mistralai\/mistral-saba", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3131256963 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.1878091774 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.4280751788 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.2100749947 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.3864616183 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.1554049163 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.3557989532 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.2229681692 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.3722031872 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2836619572 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5189927538 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.3481484827 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.5703115876 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4358717425 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6055153523 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6254747881 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7898596498 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2211802733 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.4673850088 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3141247128 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.5664089061 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2637885864 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.50661739 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.3898419239 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.5983170279 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.2931006661 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5117710763 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3454885653 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5632832845 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1846129963 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4218789485 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.2363785743 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.5715726858 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.1660483895 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4317128373 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2448276505 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4102738917 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.1159703103 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.3116167676 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.0803083214 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.3001867634 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2216993022 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.4221894818 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.1386303624 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.3369477219 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3647734864 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.5784168493 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3897396366 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5030239884 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2070601418 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4601106145 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.412349088 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6102742767 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.1710045162 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.433047449 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.2961144006 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5257430939 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.1106429776 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.3246322884 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.1586725311 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.4486820539 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.6 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.4 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.2631133201 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.504043761 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2496114121 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.4707696336 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.1854021136 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4258067424 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.1388133394 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.3685419874 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2204611632 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4366931331 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.2957932526 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5127606293 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1386896901 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.413832278 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2503925306 }, { "model":"mistralai\/mistral-small-3.1-24b-instruct", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3045084897 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2566573338 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5183862763 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3901123396 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5771753105 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2819696539 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.5293077213 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3092254935 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.4661357412 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.3052927761 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5504382993 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4246355556 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6487523813 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5178458342 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6792020066 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6631992536 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8257245236 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2800331904 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5328441069 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.3927902573 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.628791549 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2950999056 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5638983665 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.5061822417 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6903823708 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3531906075 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.6060071382 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.399293733 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6132292528 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.2559881532 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5349715693 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3900018149 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6494354052 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2100828863 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4717405627 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2844229339 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4435245651 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2977682173 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.5413323701 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2537598479 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5629521778 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.2358876365 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.4961149155 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2674122275 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4442281313 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3898113091 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.6349932626 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4218934881 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5699211354 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2989764302 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5575461672 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4347143661 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6526848356 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2156464838 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4961661832 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3525318267 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5377697887 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.2373352462 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.4812305289 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.3592771753 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.6196466978 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3847076164 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5961555843 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3031970309 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.4938747459 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2282243664 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4878680978 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2701355148 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4485608146 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2800966186 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5447813345 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3743034645 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5977965321 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.211203078 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4926704854 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2808125016 }, { "model":"openai\/gpt-4.1-mini", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3349070044 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2230716751 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.4868000305 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3431634646 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5539675011 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2104863522 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4534437048 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.2824626 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.4822940799 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.282506513 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5438865496 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.4220387975 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6440212985 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.4926163025 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6598180449 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.5627424753 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.7654936904 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2400384539 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.4846098061 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.331169359 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.541145091 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2245970544 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.4773636644 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.456500631 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6519350009 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3100386494 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5747433617 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3858833658 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.5991711103 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.1907075731 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.4662972265 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.3386484563 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.6376664219 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.5 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.6 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2240038475 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4860646744 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2284065848 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.3753787999 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.1867349669 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4122967846 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.20591358 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5231507594 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.1755855974 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.464470709 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2053629902 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4466569291 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3790281875 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.5948460259 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.4122107278 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5709045042 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.2493437671 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.4876335319 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.3816451478 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6189446172 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2106935755 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.4916756186 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.2957139688 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5505026606 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.3 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.1987953868 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.4232825095 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.2845246017 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5836686109 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3081208582 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5470122853 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.2720935434 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.4603538628 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.1864708336 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4670816214 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2648238029 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4478960511 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.2392083536 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.5109371286 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.3593480951 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.5929525126 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1574414981 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.4616304665 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2468189144 }, { "model":"openai\/gpt-4.1-nano", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3136635386 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ar", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ar", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ar", "task":"translation_from", "metric":"bleu", "score":0.2530052174 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ar", "task":"translation_from", "metric":"chrf", "score":0.5158812138 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ar", "task":"translation_to", "metric":"bleu", "score":0.3439536667 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ar", "task":"translation_to", "metric":"chrf", "score":0.5691908832 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"translation_from", "metric":"bleu", "score":0.2047894665 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"translation_from", "metric":"chrf", "score":0.4476643899 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"translation_to", "metric":"bleu", "score":0.3413387194 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"bn", "task":"translation_to", "metric":"chrf", "score":0.5056140066 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"translation_from", "metric":"bleu", "score":0.2840890109 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"translation_from", "metric":"chrf", "score":0.5146969249 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"translation_to", "metric":"bleu", "score":0.3999539422 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"de", "task":"translation_to", "metric":"chrf", "score":0.6267391818 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"translation_from", "metric":"bleu", "score":0.5232930808 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"translation_from", "metric":"chrf", "score":0.6688775695 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"translation_to", "metric":"bleu", "score":0.6469796865 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"en", "task":"translation_to", "metric":"chrf", "score":0.8203785308 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"translation_from", "metric":"bleu", "score":0.2793939864 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"translation_from", "metric":"chrf", "score":0.5176409834 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"translation_to", "metric":"bleu", "score":0.4118937163 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"es", "task":"translation_to", "metric":"chrf", "score":0.6353341411 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"translation_from", "metric":"bleu", "score":0.2706688563 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"translation_from", "metric":"chrf", "score":0.5148499232 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"translation_to", "metric":"bleu", "score":0.4808374237 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"fr", "task":"translation_to", "metric":"chrf", "score":0.6855290209 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"hi", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"hi", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"hi", "task":"translation_from", "metric":"bleu", "score":0.3473235908 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"hi", "task":"translation_from", "metric":"chrf", "score":0.5515454754 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"hi", "task":"translation_to", "metric":"bleu", "score":0.3991894826 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"hi", "task":"translation_to", "metric":"chrf", "score":0.6121310121 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"id", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"id", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"id", "task":"translation_from", "metric":"bleu", "score":0.2522725561 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"id", "task":"translation_from", "metric":"chrf", "score":0.5212732474 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"id", "task":"translation_to", "metric":"bleu", "score":0.2850030055 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"id", "task":"translation_to", "metric":"chrf", "score":0.5970450995 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"translation_from", "metric":"bleu", "score":0.2363319461 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"translation_from", "metric":"chrf", "score":0.4826308954 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"translation_to", "metric":"bleu", "score":0.2593036542 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ja", "task":"translation_to", "metric":"chrf", "score":0.4231415642 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"jv", "task":"classification", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"jv", "task":"translation_from", "metric":"bleu", "score":0.2480055389 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"jv", "task":"translation_from", "metric":"chrf", "score":0.4685108662 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"jv", "task":"translation_to", "metric":"bleu", "score":0.2241033812 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"jv", "task":"translation_to", "metric":"chrf", "score":0.5113817494 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"mr", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"mr", "task":"translation_from", "metric":"bleu", "score":0.1756463826 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"mr", "task":"translation_from", "metric":"chrf", "score":0.3823527701 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"mr", "task":"translation_to", "metric":"bleu", "score":0.2340922946 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"mr", "task":"translation_to", "metric":"chrf", "score":0.4581322597 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pa", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pa", "task":"translation_from", "metric":"bleu", "score":0.3640514137 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pa", "task":"translation_from", "metric":"chrf", "score":0.5847142015 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pa", "task":"translation_to", "metric":"bleu", "score":0.3988016179 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pa", "task":"translation_to", "metric":"chrf", "score":0.5745254523 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pt", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pt", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pt", "task":"translation_from", "metric":"bleu", "score":0.3014354397 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pt", "task":"translation_from", "metric":"chrf", "score":0.5315937202 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pt", "task":"translation_to", "metric":"bleu", "score":0.4535066637 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"pt", "task":"translation_to", "metric":"chrf", "score":0.6773057972 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"mgsm", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"mmlu", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"translation_from", "metric":"bleu", "score":0.2270580453 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"translation_from", "metric":"chrf", "score":0.5034759488 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"translation_to", "metric":"bleu", "score":0.3258505825 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ru", "task":"translation_to", "metric":"chrf", "score":0.5592402358 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"classification", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"mgsm", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"translation_from", "metric":"bleu", "score":0.222064455 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"translation_from", "metric":"chrf", "score":0.4652246692 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"translation_to", "metric":"bleu", "score":0.299635051 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"sw", "task":"translation_to", "metric":"chrf", "score":0.5860066036 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"mgsm", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"mmlu", "metric":"accuracy", "score":0.5 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"translation_from", "metric":"bleu", "score":0.3646122831 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"translation_from", "metric":"chrf", "score":0.5746253001 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"translation_to", "metric":"bleu", "score":0.3003064302 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"te", "task":"translation_to", "metric":"chrf", "score":0.5444122929 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ur", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ur", "task":"translation_from", "metric":"bleu", "score":0.2436356521 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ur", "task":"translation_from", "metric":"chrf", "score":0.4877029713 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ur", "task":"translation_to", "metric":"bleu", "score":0.2603784132 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"ur", "task":"translation_to", "metric":"chrf", "score":0.4734427307 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"vi", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"vi", "task":"mmlu", "metric":"accuracy", "score":0.7 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"vi", "task":"translation_from", "metric":"bleu", "score":0.1995232614 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"vi", "task":"translation_from", "metric":"chrf", "score":0.4582270744 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"vi", "task":"translation_to", "metric":"bleu", "score":0.2597310259 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"vi", "task":"translation_to", "metric":"chrf", "score":0.514972808 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"classification", "metric":"accuracy", "score":0.9 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"mgsm", "metric":"accuracy", "score":1.0 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"mmlu", "metric":"accuracy", "score":0.8 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"translation_from", "metric":"bleu", "score":0.1773725218 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"translation_from", "metric":"chrf", "score":0.458620733 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"translation_to", "metric":"bleu", "score":0.2753136513 }, { "model":"openai\/gpt-4o-mini", "bcp_47":"zh", "task":"translation_to", "metric":"chrf", "score":0.3274827604 } ]