Reasoning
BBH
BIG-Bench Hard — 23 tasks that require multi-step reasoning.
1 models published a score
| # | Model | Company | Score |
|---|---|---|---|
| 1 | Nova Pro | Amazon | 86.9 |
BIG-Bench Hard — 23 tasks that require multi-step reasoning.
| # | Model | Company | Score |
|---|---|---|---|
| 1 | Nova Pro | Amazon | 86.9 |