Physical Reasoning on Pooltool
36.5Att. 1 ScoreGemini-2.5-Pro
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=-2026.03 | 36.5 | 68 | |
| Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=Gemini-2.5-Pro2026.03 | 25 | 60 | |
| Qwen-7BPolicy Model=Qwen-7B, World Model=-2026.03 | 23.5 | 26.5 | |
| MOCKPolicy Model=MOCK, World Model=-2026.03 | 2.33 | 48 | |
| Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=-2026.03 | 2 | 66 | |
| Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=Qwen-7B^P2026.03 | 2 | 67.33 | |
| Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=-2026.03 | 2 | 67 | |
| Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=Qwen-7B^P&I2026.03 | 2 | 69 | |
| Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=-2026.03 | 1 | 64 | |
| Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=Qwen-7B^I2026.03 | 1 | 66.67 | |
| Qwen-3BPolicy Model=Qwen-3B, World Model=-2026.03 | 0 | 50 | |
| Qwen-32BPolicy Model=Qwen-32B, World Model=-2026.03 | 0 | 14.29 | |
| Qwen-72BPolicy Model=Qwen-72B, World Model=-2026.03 | 0 | 18 | |
| Qwen-72BPolicy Model=Qwen-72B, World Model=Qwen-72B2026.03 | 0 | 14 | |
| Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=-2026.03 | 0 | 49 | |
| Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=Claude 4.0 Opus2026.03 | 0 | 42 | |
| GPT-o3Policy Model=GPT-o3, World Model=-2026.03 | 0 | 25.67 | |
| GPT-o3Policy Model=GPT-o3, World Model=GPT-o32026.03 | 0 | 22 | |
| Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=-2026.03 | 0 | 51 | |
| Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=Qwen-3B^P2026.03 | 0 | 53.67 | |
| Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=-2026.03 | 0 | 43 | |
| Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=Qwen-3B^I2026.03 | 0 | 45.33 | |
| Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=-2026.03 | 0 | 57 | |
| Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=Qwen-3B^P&I2026.03 | 0 | 59.67 | |
| Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=-2026.03 | 0 | 58 | |
| Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=Qwen-3B^P2026.03 | 0 | 61 | |
| Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=-2026.03 | 0 | 50 | |
| Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=Qwen-3B^I2026.03 | 0 | 52.33 | |
| Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=-2026.03 | 0 | 55 | |
| Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=Qwen-3B^P&I2026.03 | 0 | 57.33 | |
| Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=-2026.03 | 0 | 66 | |
| Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=Qwen-7B^P2026.03 | 0 | 69 | |
| Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=-2026.03 | 0 | 60 | |
| Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=Qwen-7B^I2026.03 | 0 | 63 | |
| Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=-2026.03 | 0 | 69 | |
| Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=Qwen-7B^P&I2026.03 | 0 | 71 |