Physical Reasoning on Kinetix
26.89Att. 1 ScoreGPT-o3
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-o3Policy Model=GPT-o3, World Model=-2026.03 | 26.89 | |
| GPT-o3Policy Model=GPT-o3, World Model=GPT-o32026.03 | 24.5 | |
| Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=-2026.03 | 24.1 | |
| Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=-2026.03 | 23.2 | |
| Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=Gemini-2.5-Pro2026.03 | 21.8 | |
| MOCKPolicy Model=MOCK, World Model=-2026.03 | 21.4 | |
| Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=Claude 4.0 Opus2026.03 | 20.5 | |
| Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=Qwen-3B^P&I2026.03 | 19.45 | |
| Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=-2026.03 | 19.18 | |
| Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=-2026.03 | 19.18 | |
| Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=Qwen-7B^P&I2026.03 | 18.96 | |
| Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=-2026.03 | 16.44 | |
| Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=Qwen-7B^I2026.03 | 16.44 | |
| Qwen-3BPolicy Model=Qwen-3B, World Model=-2026.03 | 16.22 | |
| Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=Qwen-7B^P2026.03 | 15.31 | |
| Qwen-32BPolicy Model=Qwen-32B, World Model=-2026.03 | 15.2 | |
| Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=Qwen-3B^P&I2026.03 | 15.11 | |
| Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=-2026.03 | 15.07 | |
| Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=-2026.03 | 15.07 | |
| Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=-2026.03 | 15.07 | |
| Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=Qwen-7B^P&I2026.03 | 14.88 | |
| Qwen-72BPolicy Model=Qwen-72B, World Model=-2026.03 | 14.86 | |
| Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=Qwen-7B^P2026.03 | 13.91 | |
| Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=-2026.03 | 13.7 | |
| Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=-2026.03 | 13.7 | |
| Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=-2026.03 | 13.7 | |
| Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=Qwen-3B^P2026.03 | 13.55 | |
| Qwen-7BPolicy Model=Qwen-7B, World Model=-2026.03 | 13.51 | |
| Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=Qwen-7B^I2026.03 | 13.49 | |
| Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=-2026.03 | 12.33 | |
| Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=Qwen-3B^P2026.03 | 12.33 | |
| Qwen-72BPolicy Model=Qwen-72B, World Model=Qwen-72B2026.03 | 12.16 | |
| Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=Qwen-3B^I2026.03 | 9.82 | |
| Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=-2026.03 | 9.6 | |
| Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=-2026.03 | 8.2 | |
| Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=Qwen-3B^I2026.03 | 8.07 |