allenai/OLMo-7B-SFT
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| AlpacaEval | chat | 46.8 | low | | MPT Chat | 33.8 | 46.8 | 0.1 | 42.7 | | |
| TruthfulQA | safety | 31.6 | low | | **OLMo (base)** | 28.3 | - | 81.4 | 31.6 | | |
| MMLU | knowledge | 28.3 | low | | **OLMo (base)** | 28.3 | - | 81.4 | 31.6 | |
none scraped.