Mathematical Problem Solving on AIME 2024 (Pass@1, Pass@16)
42.19Pass@1OWPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OWPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 42.19 | 73.2 | |
| OWPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 39.9 | 54.1 | |
| MOPDModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 37.19 | 57.3 | |
| MOPDModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 36.04 | 71.17 | |
| OPDModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 35.52 | 52.2 | |
| OPDModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 35.42 | 67.36 | |
| DAPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 34.58 | 70.63 | |
| Sym-DAPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 33.23 | 63.64 | |
| Sym-DAPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 32.81 | 58.01 | |
| DAPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 31.88 | 48.84 | |
| GRPOModel=Qwen-2.5-Math-7B-Base, Checkpoint Status=Converged2026.05 | 29.79 | 48.38 | |
| GRPOModel=Qwen-3-8B-Base, Checkpoint Status=Converged2026.05 | 29.27 | 58.84 |