allenai/tulu-65b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MMLU | knowledge | 59.2 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 59.2 | 61.1 | 9.0 | 60.0 | 48.1 | 53.5 | 51.8 | 13.3 | 28.9 | 45.9 | 62.7 | 46.3 | |
| TydiQA | knowledge | 51.8 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 59.2 | 61.1 | 9.0 | 60.0 | 48.1 | 53.5 | 51.8 | 13.3 | 28.9 | 45.9 | 62.7 | 46.3 | |
| BBH | reasoning | 48.1 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 59.2 | 61.1 | 9.0 | 60.0 | 48.1 | 53.5 | 51.8 | 13.3 | 28.9 | 45.9 | 62.7 | 46.3 | |
| Codex-Eval | coding | 28.9 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 59.2 | 61.1 | 9.0 | 60.0 | 48.1 | 53.5 | 51.8 | 13.3 | 28.9 | 45.9 | 62.7 | 46.3 | |
none scraped.