Mathematical Reasoning on MATH500 (Mean@8 accuracy)
66.92Mean@8 AccuracyAsymPO
Evaluation Results
| Method | Links | |
|---|---|---|
| AsymPOModel=Qwen3-1.7B-Base, Training Data=4k subset of DAPO-17K, Evaluation Rollouts=82026.06 | 66.92 | |
| SPOModel=Qwen3-1.7B-Base, Training Data=4k subset of DAPO-17K, Evaluation Rollouts=82026.06 | 65 | |
| GRPOModel=Qwen3-1.7B-Base, Training Data=4k subset of DAPO-17K, Evaluation Rollouts=82026.06 | 63.55 |