mistral-large-latest — benchmark results
Provider: Mistral. Released 2024-07-24. Access: Open.
Unified ELO 1558 ± 21, rank #604 of 1776 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GDM InterCode CTF | 65.82 | Accuracy (%) | 57.1 |
| CyberSecEval2 Interpreter Abuse | 23.9 | Accuracy (%) | 55.6 |
| CyberSecEval2 Prompt Injection | 28.88 | Accuracy (%) | 55.6 |
| Arcadia CommonsenseQA | 83.62 | Accuracy (%) | 50 |
| AidanBench | 926 | Novel Answers | 45.5 |
| OpenAI HumanEval | 82.93 | Accuracy (%) | 45.5 |
| CyberSecEval2 Vulnerability Exploit | 38.11 | Accuracy (%) | 30 |
| ForecastBench | 59.2 | Overall Score (higher is better) | 20.5 |
Interactive version: theaggregate.ai/model?slug=mistral-large-latest · How the rankings work · Data refreshed daily, snapshot 2026-07-22.