Mathematical Reasoning on MATH500 (Score %)
76.2MATH500 ScoreINTUITOR
Evaluation Results
| Method | Links | |
|---|---|---|
| INTUITORBackbone=Qwen2.5-7B, Training Set=MATH2026.05 | 76.2 | |
| VIGORBackbone=Qwen2.5-7B, Training Set=MATH2026.05 | 76.2 | |
| GT-RewardBackbone=Qwen2.5-7B, Training Set=MATH2026.05 | 74.6 | |
| GT-RewardBackbone=Qwen2.5-3B, Training Set=MATH2026.05 | 65.6 | |
| VIGORBackbone=Qwen2.5-3B, Training Set=MATH2026.05 | 64.6 | |
| Before RL (Base)Backbone=Qwen2.5-7B, Training Set=MATH2026.05 | 63 | |
| INTUITORBackbone=Qwen2.5-3B, Training Set=MATH2026.05 | 62.4 | |
| Before RL (Base)Backbone=Qwen2.5-3B, Training Set=MATH2026.05 | 54.8 |