Physical Reasoning on Angry Birds
47.06Success RateQwen-7B^P&I GRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=Qwen-7B^P&I2026.03 | 47.06 | |
| Qwen-7B^P&I GRPOPolicy Model=Qwen-7B^P&I GRPO, World Model=-2026.03 | 45.61 | |
| Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=Qwen-7B^P&I2026.03 | 44.12 | |
| Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=Qwen-7B^P2026.03 | 44.12 | |
| Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=Qwen-7B^P2026.03 | 41.18 | |
| Qwen-7B^P&I SFTPolicy Model=Qwen-7B^P&I SFT, World Model=-2026.03 | 41.18 | |
| Qwen-7B^P GRPOPolicy Model=Qwen-7B^P GRPO, World Model=-2026.03 | 41.18 | |
| Qwen-7B^P SFTPolicy Model=Qwen-7B^P SFT, World Model=-2026.03 | 38.24 | |
| Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=-2026.03 | 35.29 | |
| GPT-o3Policy Model=GPT-o3, World Model=-2026.03 | 35.29 | |
| Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=Qwen-3B^P&I2026.03 | 35.29 | |
| Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=-2026.03 | 32.35 | |
| Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=Qwen-3B^P&I2026.03 | 32.35 | |
| Qwen-72BPolicy Model=Qwen-72B, World Model=-2026.03 | 29.41 | |
| Claude 4.0 OpusPolicy Model=Claude 4.0 Opus, World Model=Claude 4.0 Opus2026.03 | 29.41 | |
| Gemini-2.5-ProPolicy Model=Gemini-2.5-Pro, World Model=Gemini-2.5-Pro2026.03 | 29.41 | |
| GPT-o3Policy Model=GPT-o3, World Model=GPT-o32026.03 | 29.41 | |
| Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=Qwen-3B^P2026.03 | 29.41 | |
| Qwen-3B^P&I GRPOPolicy Model=Qwen-3B^P&I GRPO, World Model=-2026.03 | 29.41 | |
| Qwen-32BPolicy Model=Qwen-32B, World Model=-2026.03 | 26.47 | |
| Qwen-72BPolicy Model=Qwen-72B, World Model=Qwen-72B2026.03 | 26.47 | |
| Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=Qwen-3B^P2026.03 | 26.47 | |
| Qwen-3B^P&I SFTPolicy Model=Qwen-3B^P&I SFT, World Model=-2026.03 | 26.47 | |
| Qwen-3B^P GRPOPolicy Model=Qwen-3B^P GRPO, World Model=-2026.03 | 26.47 | |
| Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=Qwen-7B^I2026.03 | 26.47 | |
| Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=Qwen-7B^I2026.03 | 26.47 | |
| Qwen-3B^P SFTPolicy Model=Qwen-3B^P SFT, World Model=-2026.03 | 23.53 | |
| Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=Qwen-3B^I2026.03 | 23.53 | |
| Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=Qwen-3B^I2026.03 | 23.53 | |
| Qwen-7B^I SFTPolicy Model=Qwen-7B^I SFT, World Model=-2026.03 | 23.53 | |
| Qwen-7B^I GRPOPolicy Model=Qwen-7B^I GRPO, World Model=-2026.03 | 23.53 | |
| Qwen-7BPolicy Model=Qwen-7B, World Model=-2026.03 | 20.59 | |
| Qwen-3B^I SFTPolicy Model=Qwen-3B^I SFT, World Model=-2026.03 | 20.59 | |
| Qwen-3B^I GRPOPolicy Model=Qwen-3B^I GRPO, World Model=-2026.03 | 20.59 | |
| MOCKPolicy Model=MOCK, World Model=-2026.03 | 17.65 | |
| Qwen-3BPolicy Model=Qwen-3B, World Model=-2026.03 | 17.65 |