Mathematical Reasoning on AMC 23 (pass@4, pass@8, pass@16)
93.49Pass@4Qwen2.5-7B EP-GRPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen2.5-7B EP-GRPOModel=Qwen2.5-7B, Method=EP-GRPO2026.05 | 93.49 | 99.59 | 100 | |
| Qwen2.5-7B GRPOModel=Qwen2.5-7B, Method=GRPO2026.05 | 92.29 | 99.42 | 100 | |
| Qwen2.5-3B EP-GRPOModel=Qwen2.5-3B, Method=EP-GRPO2026.05 | 86.71 | 98.26 | 99.97 | |
| Qwen2.5-3B GRPO (Higher Temp)Model=Qwen2.5-3B, Method=GRPO, Temperature=Higher2026.05 | 78.95 | 95.62 | 99.82 | |
| Qwen2.5-3B GRPO (More Rollouts)Model=Qwen2.5-3B, Method=GRPO, Rollouts=More2026.05 | 76.51 | 94.54 | 99.72 | |
| Qwen2.5-3B GRPOModel=Qwen2.5-3B, Method=GRPO2026.05 | 73.64 | 93.12 | 99.55 | |
| Qwen2.5-7B BaseModel=Qwen2.5-7B, Method=Base2026.05 | 65.17 | 87.96 | 98.6 | |
| Qwen3-235B-A22B-InstructModel=Qwen3-235B-A22B-Instruct, Category=Commercial Models2026.05 | 59.66 | 63 | 65 | |
| DeepSeek-R1-671B-0528Model=DeepSeek-R1-671B-0528, Category=Commercial Models2026.05 | 58.72 | 66.19 | 72.5 | |
| Qwen2.5-3B BaseModel=Qwen2.5-3B, Method=Base2026.05 | 50.15 | 75.27 | 94 |