allenai/digital-socrates-13b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| HellaSwag | knowledge | 80.14 | HellaSwag (10-Shot) | medium | | HellaSwag (10-Shot) | 80.14 | |
| WinoGrande | knowledge | 74.59 | Winogrande (5-shot) | medium | | Winogrande (5-shot) | 74.59 | |
| MMLU | knowledge | 57.01 | MMLU (5-Shot) | medium | | MMLU (5-Shot) | 57.01 | |
| TruthfulQA | safety | 44.47 | TruthfulQA (0-shot) | medium | | TruthfulQA (0-shot) | 44.47 | |
| GSM8K | math | 29.49 | GSM8k (5-shot) | medium | | GSM8k (5-shot) | 29.49 | |
none scraped.