Hercules-3.1-Mistral-7B: benchmark results
Provider: Locutusque. Released 2024-02-01. Access: Open.
Aggregate Rating 1406 ± 31, rank #5820 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical LLM - PubMedQA | 75.6 | Accuracy (%) | 76 |
| Open LLM Leaderboard v1 - WinoGrande | 79.01 | Accuracy (%) (5-shot) | 66.7 |
| Open LLM Leaderboard v1 - MMLU | 63.65 | Accuracy (%) (5-shot) | 62.2 |
| Open LLM Leaderboard v1 - HellaSwag | 83.55 | Normalized accuracy (%) (10-shot) | 59.6 |
| Open LLM Leaderboard v1 - GSM8K | 42.3 | Accuracy (%) (5-shot) | 57 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.18 | Normalized accuracy (%) (25-shot) | 51.6 |
| Open Medical LLM - MMLU College Medicine | 61.85 | Accuracy (%) | 47.7 |
| Open Medical LLM - MMLU Professional Medicine | 68.38 | Accuracy (%) | 44 |
| Open Medical LLM - MMLU College Biology | 71.53 | Accuracy (%) | 39.6 |
| Open Medical LLM - MedMCQA | 48.53 | Accuracy (%) | 39.6 |
| Open Medical LLM - MedQA (USMLE) | 51.22 | Accuracy (%) | 37 |
| Open Medical-LLM Leaderboard (BenchmarkList) | 63.09 | Medical average (%) | 36.1 |
Interactive version: theaggregate.ai/model?slug=hercules-3-1-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.