allenai/OLMo-7B-0724-SFT-hf
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| AlpacaEval | chat | 70.9 | low | | **[OLMo 7B July 2024 SFT](https://huggingface.co/allenai/OLMo-1.7-7B-Nitro-SFT-hf)** | 54.2 | 70.9 | .1 | 44.4 | | |
| MMLU | knowledge | 50.8 | low | | **OLMo July 2024 base** | 50.8 | - | 85.2 | 28.4 | | |
| TruthfulQA | safety | 28.4 | low | | **OLMo July 2024 base** | 50.8 | - | 85.2 | 28.4 | |
none scraped.