BioMistral-7B-DARE: benchmark results
Provider: Avignon Univ. Released 2024-02-01. Access: Open.
Aggregate Rating 1365 ± 32, rank #7313 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical LLM - PubMedQA | 77.6 | Accuracy (%) | 94 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.61 | MC2 (%) (0-shot) | 65.5 |
| Open LLM Leaderboard v1 - WinoGrande | 76.09 | Accuracy (%) (5-shot) | 45.9 |
| Open LLM Leaderboard v1 - MMLU | 57.34 | Accuracy (%) (5-shot) | 40.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.28 | Normalized accuracy (%) (25-shot) | 39.4 |
| Open LLM Leaderboard v1 - HellaSwag | 79.87 | Normalized accuracy (%) (10-shot) | 39.4 |
| Open LLM Leaderboard v1 - GSM8K | 15.01 | Accuracy (%) (5-shot) | 37 |
| Open Medical LLM - MMLU Clinical Knowledge | 66.42 | Accuracy (%) | 32 |
| Open Medical LLM - MMLU College Medicine | 58.96 | Accuracy (%) | 31.5 |
| Open Medical LLM - MMLU Medical Genetics | 68 | Accuracy (%) | 29.2 |
| Open Medical LLM - MedQA (USMLE) | 47.37 | Accuracy (%) | 28.6 |
| Open Medical LLM - MMLU Anatomy | 53.33 | Accuracy (%) | 28.1 |
Interactive version: theaggregate.ai/model?slug=biomistral-7b-dare · How It Works · Data refreshed daily, snapshot 2026-11-08.