mistralai/Mistral-Nemo-Base-2407
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| HellaSwag | knowledge | 83.5 | HellaSwag (0-shot) | medium | | HellaSwag (0-shot) | 83.5% | |
| WinoGrande | knowledge | 76.8 | Winogrande (0-shot) | medium | | Winogrande (0-shot) | 76.8% | |
| TriviaQA | knowledge | 73.8 | TriviaQA (5-shot) | medium | | TriviaQA (5-shot) | 73.8% | |
| CommonsenseQA | knowledge | 70.4 | CommonSenseQA (0-shot) | medium | | CommonSenseQA (0-shot) | 70.4% | |
| MMLU | knowledge | 68.0 | MMLU (5-shot) | medium | | MMLU (5-shot) | 68.0% | |
| OpenBookQA | knowledge | 60.6 | OpenBookQA (0-shot) | medium | | OpenBookQA (0-shot) | 60.6% | |
| TruthfulQA | safety | 50.3 | TruthfulQA (0-shot) | medium | | TruthfulQA (0-shot) | 50.3% | |
none scraped.