[ { "Model": "llama-3.1-8b", "CR": "61.3", "S-Acc": "23.3", "EM": "0.0", "PM-0.5": "14.0", "Tokens": "2887" }, { "Model": "llama-3.1-70b", "CR": "77.3", "S-Acc": "46.8", "EM": "0.0", "PM-0.5": "62.0", "Tokens": "3071" }, { "Model": "llama-3.3-70b", "CR": "85.3", "S-Acc": "47.6", "EM": "0.0", "PM-0.5": "65.3", "Tokens": "2612" }, { "Model": "mistral-7b", "CR": "94.0", "S-Acc": "23.0", "EM": "0.0", "PM-0.5": "6.7", "Tokens": "3655" }, { "Model": "mistral-small-22b", "CR": "98.7", "S-Acc": "48.3", "EM": "0.0", "PM-0.5": "54.0", "Tokens": "3134" }, { "Model": "mistral-large-123b", "CR": "99.3", "S-Acc": "62.8", "EM": "2.0", "PM-0.5": "86.0", "Tokens": "3237" }, { "Model": "qwen-2.5-7b", "CR": "98.7", "S-Acc": "21.1", "EM": "0.0", "PM-0.5": "3.3", "Tokens": "2441" }, { "Model": "qwen-2.5-32b", "CR": "100.0", "S-Acc": "34.6", "EM": "0.0", "PM-0.5": "20.0", "Tokens": "2560" }, { "Model": "qwen-2.5-72b", "CR": "100.0", "S-Acc": "44.1", "EM": "0.0", "PM-0.5": "36.7", "Tokens": "2734" }, { "Model": "qwq-32b", "CR": "80.0", "S-Acc": "30.2", "EM": "0.0", "PM-0.5": "18.0", "Tokens": "4816" }, { "Model": "deepseek-R1", "CR": "100.0", "S-Acc": "75.3", "EM": "16.7", "PM-0.5": "94.0", "Tokens": "9809" }, { "Model": "gemini-2.0-exp", "CR": "98.7", "S-Acc": "61.6", "EM": "0.0", "PM-0.5": "83.3", "Tokens": "2555" }, { "Model": "gemini-2.0-thinking", "CR": "94.7", "S-Acc": "57.7", "EM": "1.3", "PM-0.5": "79.3", "Tokens": "2648" }, { "Model": "openai-gpt-4o", "CR": "100.0", "S-Acc": "63.0", "EM": "1.3", "PM-0.5": "86.7", "Tokens": "1726" }, { "Model": "openai-o1-mini", "CR": "95.3", "S-Acc": "45.5", "EM": "1.3", "PM-0.5": "54.0", "Tokens": "7840" }, { "Model": "openai-o1-preview", "CR": "98.0", "S-Acc": "77.7", "EM": "24.7", "PM-0.5": "89.3", "Tokens": "10098" } ]