Mathematical Reasoning on Olympiad (pass@1 mean and std)
63.2Pass@1 MeanDAPO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DAPOSampling strategy=avg@4, Number of repeats=42026.01 | 63.2 | 6.8 | |
| ReNCESampling strategy=avg@4, Number of repeats=42026.01 | 62.6 | 9.7 | |
| Semi-online DPOSampling strategy=avg@4, Number of repeats=42026.01 | 59.6 | 5.7 | |
| GRPOSampling strategy=avg@4, Number of repeats=42026.01 | 58.5 | 7.2 | |
| No trainingSampling strategy=avg@4, Number of repeats=42026.01 | 44.7 | 7 |