Science Reasoning on TAL-SCQ5K EN
73Pass@1MIG
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MIGEvaluation Mode=In-Domain, Training Strategy=Task-Specific Training2026.02 | 73 | 90 | 11 | |
| Base ModelEvaluation Mode=In-Domain, Training Strategy=Task-Specific Training2026.02 | 64 | 86 | — | |
| GRPOEvaluation Mode=In-Domain, Training Strategy=Task-Specific Training2026.02 | 62 | 81 | — |