List your company

Physical Reasoning on PHYRE DeepPHY (test)

14.92Att. 1 ScoreQwen-7B^P&I GRPO
-0.56563.45477.47511.4953Mar 1, 2026

Evaluation results

MethodLinks
Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=Qwen-7B^P&I2026.0314.9245.56
Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=-2026.0314.6343.17
Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=Qwen-3B^P&I2026.0314.1139.49
Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=-2026.031434.5
Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=Qwen-7B^P2026.0313.1843.66
Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=-2026.031340
Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=Qwen-3B^P&I2026.0310.733.56
Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=-2026.0310.4229
Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=Qwen-3B^P2026.039.8532
Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=-2026.039.529.03
Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=Qwen-7B^P&I2026.037.9544.85
Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=-2026.037.542.67
Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=-2026.033.6736.13
Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=Qwen-7B^P2026.033.438.67
GPT-o3Policy Model=GPT-o3, World Model=-2026.033.0330.77
Qwen-72BPolicy Model=Qwen-72B, World Model=-2026.032.4314.92
Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=-2026.032.1722.07
Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=Gemini-2.5-Pro2026.032.1712.33
Qwen-72BPolicy Model=Qwen-72B, World Model=Qwen-72B2026.031.7810.39
Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=-2026.031.7310.63
Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=Qwen-3B^P2026.031.5228.69
MOCKPolicy Model=MOCK, World Model=-2026.031.510.8
Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=-2026.031.3325.58
Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=Claude 4.0 Opus2026.031.117.44
Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=Qwen-7B^I2026.030.8213.45
Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=Qwen-3B^I2026.030.7411.88
Qwen-7BPolicy Model=Qwen-7B, World Model=-2026.030.6710.1
Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=-2026.030.679.33
Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=-2026.030.678.33
Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=Qwen-7B^I2026.030.6713.04
Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=Qwen-3B^I2026.030.6613.48
Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=-2026.030.339.83
Qwen-3BPolicy Model=Qwen-3B, World Model=-2026.030.175.85
GPT-o3Policy Model=GPT-o3, World Model=GPT-o32026.030.1725.6
Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=-2026.030.179.67
Qwen-32BPolicy Model=Qwen-32B, World Model=-2026.030.038.7