Mathematical Reasoning on Aggregate (MATH500, GSM8K, GAO23, MINERVA, OLYM, AIME24, AIME25, AMC23)
44.94Average ScoreQwen2.5-Math-1.5B + CurES-GRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-Math-1.5B + CurES-GRPOBackbone=Qwen2.5-Math-1.5B, Training Method=CurES-GRPO2025.10 | 44.94 | |
| Qwen2.5-Math-1.5B + MoPPSBackbone=Qwen2.5-Math-1.5B, Training Method=MoPPS2025.10 | 43.98 | |
| Qwen2.5-Math-1.5B + DAPOBackbone=Qwen2.5-Math-1.5B, Training Method=DAPO2025.10 | 42.8 | |
| Qwen2.5-Math-1.5BBackbone=Qwen2.5-Math-1.5B, Training Method=Base2025.10 | 20 |