Accuracy on General Science Question Answering on GPQA
0.5455Accuracy (GPQA)OWPO
Evaluation Results
| Method | Links | |
|---|---|---|
| OWPOModel=Qwen-3-8B-Base2026.05 | 0.5455 | |
| DAPOModel=Qwen-3-8B-Base2026.05 | 0.5227 | |
| OPDModel=Qwen-3-8B-Base2026.05 | 0.5227 | |
| MOPDModel=Qwen-3-8B-Base2026.05 | 0.5051 | |
| GRPOModel=Qwen-3-8B-Base2026.05 | 0.5044 | |
| Sym-DAPOModel=Qwen-3-8B-Base2026.05 | 0.5012 | |
| OWPOModel=Qwen-2.5-Math-7B-Base2026.05 | 0.4103 | |
| OPDModel=Qwen-2.5-Math-7B-Base2026.05 | 0.3939 | |
| DAPOModel=Qwen-2.5-Math-7B-Base2026.05 | 0.3927 | |
| MOPDModel=Qwen-2.5-Math-7B-Base2026.05 | 0.3876 | |
| Sym-DAPOModel=Qwen-2.5-Math-7B-Base2026.05 | 0.3725 | |
| GRPOModel=Qwen-2.5-Math-7B-Base2026.05 | 0.3434 |