mlabonne/NeuralDarewin-7B
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| HellaSwag | knowledge | 86.4 | HellaSwag (10-Shot) | medium | | HellaSwag (10-Shot) | 86.40 | |
| WinoGrande | knowledge | 79.72 | Winogrande (5-shot) | medium | | Winogrande (5-shot) | 79.72 | |
| GSM8K | math | 66.72 | GSM8k (5-shot) | medium | | GSM8k (5-shot) | 66.72 | |
| MMLU | knowledge | 64.85 | MMLU (5-Shot) | medium | | MMLU (5-Shot) | 64.85 | |
| TruthfulQA | safety | 62.92 | TruthfulQA (0-shot) | medium | | TruthfulQA (0-shot) | 62.92 | |
none scraped.