Math on Math (val)
100Pass@16GRPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GRPODifficulty=Easy, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 100 | 95.3 | |
| CoRPODifficulty=Easy, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 100 | 93.8 | |
| GRPODifficulty=Easy, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 100 | 94.5 | |
| CoRPODifficulty=Easy, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 100 | 97.3 | |
| GRPODifficulty=Medium, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 100 | 78.2 | |
| CoRPODifficulty=Medium, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 100 | 82.3 | |
| CoRPODifficulty=Medium, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 97.3 | 79.1 | |
| GRPODifficulty=Medium, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 91.9 | 75.2 | |
| CoRPODifficulty=Overall, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 90.1 | 61.7 | |
| GRPODifficulty=Overall, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 89.3 | 63 | |
| GRPODifficulty=Overall, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 88.8 | 60.2 | |
| CoRPODifficulty=Overall, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 88.4 | 61.5 | |
| GRPODifficulty=Hard, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 82.5 | 41.1 | |
| CoRPODifficulty=Hard, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 81.2 | 35.9 | |
| CoRPODifficulty=Hard, Validation Set Domain=In-domain, Train Set=Math, MSL=16k, Temperature=0.32025.11 | 78.8 | 37.8 | |
| GRPODifficulty=Hard, Validation Set Domain=Out-of-domain, Train Set=Coding, MSL=16k, Temperature=0.32025.11 | 78.8 | 35.7 |