MathHermes-2.5-Mistral-7B: benchmark results
Provider: Other.
Aggregate Rating 1414 ± 33, rank #5475 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 64.76 | Normalized accuracy (%) (25-shot) | 67.9 |
| Open LLM Leaderboard v1 - HellaSwag | 84.19 | Normalized accuracy (%) (10-shot) | 64.4 |
| Open LLM Leaderboard v1 - GSM8K | 49.28 | Accuracy (%) (5-shot) | 62.1 |
| Open LLM Leaderboard v1 - MMLU | 63.59 | Accuracy (%) (5-shot) | 61.7 |
| Open LLM Leaderboard v1 - WinoGrande | 77.66 | Accuracy (%) (5-shot) | 57.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.95 | MC2 (%) (0-shot) | 53.9 |
Interactive version: theaggregate.ai/model?slug=mathhermes-2-5-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.