allenai/open-instruct-unnatural-instructions-7b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MMLU | knowledge | 42.9 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 42.9 | 38.1 | 3.5 | 5.0 | 31.4 | 30.0 | 36.3 | 6.5 | 10.3 | 19.8 | 8.2 | 20.0 | |
| TydiQA | knowledge | 36.3 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 42.9 | 38.1 | 3.5 | 5.0 | 31.4 | 30.0 | 36.3 | 6.5 | 10.3 | 19.8 | 8.2 | 20.0 | |
| BBH | reasoning | 31.4 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 42.9 | 38.1 | 3.5 | 5.0 | 31.4 | 30.0 | 36.3 | 6.5 | 10.3 | 19.8 | 8.2 | 20.0 | |
| Codex-Eval | coding | 10.3 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 42.9 | 38.1 | 3.5 | 5.0 | 31.4 | 30.0 | 36.3 | 6.5 | 10.3 | 19.8 | 8.2 | 20.0 | |
none scraped.