Chain-of-thought Reasoning on BBH (CoT)
54.42Accuracy (BBH CoT)Baseline
Evaluation Results
| Method | Links | |
|---|---|---|
| Baseline2026.05 | 54.42 | |
| InFamilySteer2026.05 | 54.26 | |
| DenseSteer2026.05 | 54.05 |
| Method | Links | |
|---|---|---|
| Baseline2026.05 | 54.42 | |
| InFamilySteer2026.05 | 54.26 | |
| DenseSteer2026.05 | 54.05 |