alpindale/WizardLM-2-8x22B
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| IFEval | instruction-following | 52.72 | IFEval (0-Shot) | medium | | IFEval (0-Shot) | 52.72 | |
| BBH | reasoning | 48.58 | BBH (3-Shot) | medium | | BBH (3-Shot) | 48.58 | |
| MMLU-Pro | knowledge | 39.96 | MMLU-PRO (5-shot) | medium | | MMLU-PRO (5-shot) | 39.96 | |
| MATH | math | 22.28 | MATH Lvl 5 (4-Shot) | medium | | MATH Lvl 5 (4-Shot) | 22.28 | |
| GPQA | reasoning | 17.56 | GPQA (0-shot) | medium | | GPQA (0-shot) | 17.56 | |
| MUSR | reasoning | 14.54 | MuSR (0-shot) | medium | | MuSR (0-shot) | 14.54 | |
none scraped.