Mathematical Problem Solving on AIME 2025 (Pass@1, Pass@16)
31.67Pass@1OWPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OWPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 31.67 | 49.24 | |
| DAPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 30.63 | 52.35 | |
| MOPDModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 27.19 | 49.84 | |
| OPDModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 26.56 | 49.52 | |
| Sym-DAPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 24.79 | 51.33 | |
| GRPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 20.42 | 45.02 | |
| OWPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 18.44 | 31.18 | |
| DAPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 17.29 | 32.27 | |
| MOPDModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 16.98 | 34.14 | |
| OPDModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 16.56 | 37.38 | |
| Sym-DAPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 15.63 | 32.52 | |
| GRPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 12.6 | 26.99 |