Competition Mathematics on AIME 2024 (Accuracy avg@4)
34.5Accuracy (avg@4)PAPO
Evaluation Results
| Method | Links | |
|---|---|---|
| PAPOModel=Qwen3-4B-Base2026.03 | 34.5 | |
| ORM(DAPO)Model=Qwen3-4B-Base2026.03 | 30.8 | |
| PAPOModel=Qwen2.5-14B2026.03 | 24.3 | |
| ORM(GRPO)Model=Qwen2.5-14B2026.03 | 19 | |
| PAPOModel=Qwen2.5-7B2026.03 | 15.8 | |
| BaseModel=Qwen3-4B-Base2026.03 | 11.2 | |
| ORM(GRPO)Model=Qwen2.5-7B2026.03 | 10.8 | |
| BaseModel=Qwen2.5-14B2026.03 | 10.8 | |
| PAPOModel=Qwen2.5-3B2026.03 | 10 | |
| ORM(GRPO)Model=Qwen2.5-3B2026.03 | 8.3 | |
| BaseModel=Qwen2.5-7B2026.03 | 5 | |
| BaseModel=Qwen2.5-3B2026.03 | 2.5 |