allenai/digital-socrates-7b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| HellaSwag | knowledge | 75.99 | HellaSwag (10-Shot) | medium | | HellaSwag (10-Shot) | 75.99 | |
| WinoGrande | knowledge | 73.09 | Winogrande (5-shot) | medium | | Winogrande (5-shot) | 73.09 | |
| MMLU | knowledge | 51.41 | MMLU (5-Shot) | medium | | MMLU (5-Shot) | 51.41 | |
| TruthfulQA | safety | 44.88 | TruthfulQA (0-shot) | medium | | TruthfulQA (0-shot) | 44.88 | |
| GSM8K | math | 17.89 | GSM8k (5-shot) | medium | | GSM8k (5-shot) | 17.89 | |
none scraped.