Mathematical Reasoning on MATH (Pass@k Set)
61.4Pass@1MIG
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MIGEvaluation Mode=In-Domain, Training Strategy=Task-Specific Training2026.02 | 61.4 | 81 | 3.4 | |
| GRPOEvaluation Mode=In-Domain, Training Strategy=Task-Specific Training2026.02 | 58 | 80.2 | — | |
| Base ModelEvaluation Mode=In-Domain, Training Strategy=Task-Specific Training2026.02 | 56.2 | 76 | — |