CathieDaDa/Reasoning_Capability_Leaderboard

1排名,模型名称,综合得分21,豆包1.5 Pro（思考模式）,9332,GPT-5（自动模式）,91.543,GPT-o3,9154,豆包1.5 Pro,90.565,DeepSeek-R1,89.575,Gemini 2.5 Pro,89.585,通义千问3（思考模式）,89.598,混元-T1,88.5108,文心一言 X1-Turbo,88.51110,Gemini 2.5 flash,881210,Grok 3（思考模式）,881312,通义千问3,871413,GPT-4.1,861514,DeepSeek-V3,851614,GPT-o4 mini,851716,GPT-4o,84.51817,混元-TurboS,83.51918,Claude 4 Opus （思考模式）,832019,Claude 4 Opus,82.52119,Grok 3,82.52219,Grok 4,82.52322,文心一言4.5-Turbo,80.52423,MiniMax-01,802523,日日新 V6 Pro,802623,日日新 V6推理,802726,Yi- Lightning,79.52827,GLM-4-plus,782928,Kimi,77.53028,Spark 4.0 Ultra,77.53130,Step 2,76.53230,GLM-Z1-Air,763332,Baichuan4-Turbo,75.53433,Step R1-V-Mini,71.53534,360智脑2-o1,703635,Llama 3.3 70B,69.53736,Kimi-k1.5,69