allenai/open-instruct-dolly-7b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| TydiQA | knowledge | 43.6 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 38.0 | 35.8 | 5.0 | 7.0 | 27.2 | 24.4 | 43.6 | 8.7 | 11.1 | 22.1 | 12.7 | 20.7 | |
| MMLU | knowledge | 38.0 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 38.0 | 35.8 | 5.0 | 7.0 | 27.2 | 24.4 | 43.6 | 8.7 | 11.1 | 22.1 | 12.7 | 20.7 | |
| BBH | reasoning | 27.2 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 38.0 | 35.8 | 5.0 | 7.0 | 27.2 | 24.4 | 43.6 | 8.7 | 11.1 | 22.1 | 12.7 | 20.7 | |
| Codex-Eval | coding | 11.1 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 38.0 | 35.8 | 5.0 | 7.0 | 27.2 | 24.4 | 43.6 | 8.7 | 11.1 | 22.1 | 12.7 | 20.7 | |
none scraped.