mistral-7B-openhermes-sft: benchmark results
Provider: CorticalStack. Access: Open.
Aggregate Rating 1387 ± 33, rank #6628 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 77.58 | Accuracy (%) (5-shot) | 57 |
| Open LLM Leaderboard v1 - MMLU | 60.95 | Accuracy (%) (5-shot) | 50.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.58 | Normalized accuracy (%) (25-shot) | 48.4 |
| Open LLM Leaderboard v1 - HellaSwag | 82.01 | Normalized accuracy (%) (10-shot) | 48.3 |
| Open LLM Leaderboard v1 - GSM8K | 31.24 | Accuracy (%) (5-shot) | 48.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.31 | MC2 (%) (0-shot) | 34 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-openhermes-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.