Compositionality on CoGenT
91Pass@1MIG
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MIGevaluation_mode=In-Domain, training_protocol=Task-Specific Training2026.02 | 91 | 98 | 9 | |
| GRPOevaluation_mode=In-Domain, training_protocol=Task-Specific Training2026.02 | 82 | 95 | — | |
| Base Modelevaluation_mode=In-Domain, training_protocol=Task-Specific Training2026.02 | 54 | 79 | — |