allenai/open-instruct-baize-7b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MMLU | knowledge | 40.3 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 | |
| BBH | reasoning | 30.6 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 | |
| TydiQA | knowledge | 29.8 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 | |
| Codex-Eval | coding | 12.2 | GSM CoT | BBH CoT | TydiQA Closed-book | low | | 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 | |
none scraped.