CathieDaDa/Reasoning_Capability_Leaderboard_en

1Ranking,Model Name,Basic Logical Inference (Weighted Score)21,GPT-o3,9732,Doubao 1.5 Pro,9643,Doubao 1.5 Pro (Thinking),9554,GPT-5 (Auto),9465,DeepSeek-R1,9276,Qwen 3 (Thinking),9087,Gemini 2.5 Pro,8897,GPT-o4 mini,88107,Hunyuan-T1,88117,Ernie X1-Turbo,881211,GPT-4.1,871311,GPT-4o,871411,Qwen 3,871514,DeepSeek-V3,861614,Grok 3 (Thinking),861714,SenseChat V6 (Thinking),861817,Claude 4 Opus,851917,Claude 4 Opus thinking,852019,Gemini 2.5 Flash,842120,SenseChat V6 Pro,832221,Hunyuan-TurboS,812322,Baichuan4-Turbo,802422,Grok 3,802522,Grok 4,802622,Yi- Lightning,802726,MiniMax-01,792827,Spark 4.0 Ultra,772927,Step R1-V-Mini,773029,GLM-4-plus,763129,GLM-Z1-Air,763229,Kimi,763332,Ernie 4.5-Turbo,743433,Step 2,733534,Kimi-k1.5,723635,Llama 3.3 70B,643736,360 Zhinao 2-o1,59