Mathematical Reasoning on Game of 24 (pass@1, djump)
0.84pass@1BoN w. ReJump
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BoN w. ReJumpModel=Phi-4-reasoning-plus2025.11 | 0.84 | 5.53 | |
| BoN w. ReJumpModel=QwQ-32B2025.11 | 0.82 | 5.7 | |
| Weighted MV w. ReJumpModel=Phi-4-reasoning-plus2025.11 | 0.81 | 4.02 | |
| Weighted MV w. ReJumpModel=QwQ-32B2025.11 | 0.8 | 5.09 | |
| Majority Vote (MV)Model=Phi-4-reasoning-plus2025.11 | 0.77 | 3.32 | |
| Majority Vote (MV)Model=QwQ-32B2025.11 | 0.76 | 4.2 |