mistral-large-latest: benchmark results
Provider: Mistral. Released 2024-07-24.
Aggregate Rating 1569 ± 33, rank #1423 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Bias Risk | 39.53 | Risk Score | 95.9 |
| Enkrypt AI - Safety Risk | 20.03 | Risk Score | 84.9 |
| GDM InterCode CTF | 65.82 | Accuracy (%) | 57.1 |
| Arcadia CommonsenseQA | 83.62 | Accuracy (%) | 50 |
| Enkrypt AI - Risk Score | 32.8 | Risk Score | 45.9 |
| AidanBench | 926 | Novel Answers | 45.5 |
| OpenAI HumanEval | 82.93 | Accuracy (%) | 45.5 |
| CyberSecEval2 Interpreter Abuse | 23.9 | Malicious Compliance Rate (%) | 44.4 |
| CyberSecEval2 Prompt Injection | 28.88 | Injection Success Rate (%) | 44.4 |
| Enkrypt AI - Jailbreak Risk | 11.84 | Risk Score | 34.2 |
| CyberSecEval2 Vulnerability Exploit | 38.11 | Accuracy (%) | 30 |
| Enkrypt AI - Insecure Code Risk | 45.78 | Risk Score | 26.9 |
Interactive version: theaggregate.ai/model?slug=mistral-large-latest · How It Works · Data refreshed daily, snapshot 2026-11-08.