List your company

Reasoning on GSM8K (p_T/p_S Evaluation)

97.1p_T ScoreO3
75.57281.16186.7592.339Oct 20, 2025

Evaluation results

MethodLinks
O32025.1097.1193.61-3.595.592.31
GPT-5-minisize=mini2025.1096.9180.17-16.871.473.36
Kimi-K22025.1096.8181.66-15.292.579.74
GPT-52025.1096.81826-14.781.477.55
O12025.1096.5282.75-13.897823
O4-minisize=mini2025.1096.5269.411-27.194.968.49
GPT-5-chatmode=chat2025.1096.4256.214-40.285.253.713
DeepSeek-V32025.1096.3275.39-2169.868.49
Llama-3.3-Instparameters=70B2025.1096.2289.53-6.751.976.66
DeepSeek-R12025.1096.1279.28-16.875.873.56
O3-minisize=mini2025.1096.1291.62-4.529.472.27
GPT-4o2025.1095.9384.24-11.748.471.28
Qwen2.5-Instparameters=72B2025.1095.7363.812-31.956.755.512
GPT-4.1-minisize=mini, version=4.12025.1095.5370.410-25.177.865.710
GPT-42025.1095.1488.33-6.883.184.32
GPT-4.1version=4.12025.1095.1470.310-24.890.168.29
GPT-5-nanosize=nano2025.1094.8484.44-10.415.56311
Phi-42025.1094.2584.54-9.735.268.19
O1-minisize=mini2025.1093.3659.613-33.778.755.812
Ministral-Instparameters=8B, version=24102025.1086.1755.914-30.263.849.814
GPT-3.52025.1076.4740.215-36.25034.515