Mistral 7B Instruct (v0.2): benchmark results
Provider: Mistral. Released 2023-12-11. Access: Open.
Unified ELO 1391 ± 1, rank #1173 of 1392 rated models, from 175 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AlpacaEval 1.0 | 92.78 | Win Rate (%) | 84.2 |
| Open Chinese LLM - TruthfulQA MC | 58.78 | Accuracy (%) | 78.6 |
| SpeechMap Compliance | 81.5 | % Requests Completed | 78.6 |
| EconLogicQA | 0.32 | Accuracy | 76.5 |
| CyberMetric | 77.09 | Accuracy (%) | 75 |
| MERA - ruCodeEval | 27.5 | pass@1 (%) | 70.8 |
| MERA - ruHumanEval | 25.98 | pass@1 (%) | 69.7 |
| BiGGen-Bench | 3.62 | Average Score (1-5) | 69.6 |
| MERA - RWSD | 60 | Accuracy (%) | 68.7 |
| Open LLM Leaderboard - IFEval | 54.96 | Score | 66.3 |
| Enkrypt AI - Toxicity Risk | 2.09 | Risk Score | 65.8 |
| Open CoT - LogiQA | 5.27 | CoT Gain (%) | 65.6 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-05.