Mixtral-8x7B-Instruct-v0.1 [float16] [rev: 125c431e2ff4]: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1472 ± 33, rank #2797 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 71.4 | Accuracy (%) (5-shot) | 95 |
| Open LLM Leaderboard v1 - HellaSwag | 87.55 | Normalized accuracy (%) (10-shot) | 86.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.14 | Normalized accuracy (%) (25-shot) | 85.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 64.98 | MC2 (%) (0-shot) | 82.9 |
| Open LLM Leaderboard v1 - WinoGrande | 81.06 | Accuracy (%) (5-shot) | 77 |
| Open LLM Leaderboard v1 - GSM8K | 61.11 | Accuracy (%) (5-shot) | 73.5 |
Interactive version: theaggregate.ai/model?slug=mixtral-8x7b-instruct-v0-1-float16-rev-125c431e2ff4 · How It Works · Data refreshed daily, snapshot 2026-11-08.