Mistral Large 4 (High): benchmark results
Provider: Mistral. Released 2026-10-06. Access: API.
Unified ELO 1760 ± 25, rank #216 of 2136 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LiveBench Table Reformat | 100 | Score | 81.6 |
| LiveBench Math Comp | 97.06 | Score | 80.1 |
| LiveBench Python | 60 | Score | 72.1 |
| LiveBench Integrals With Game | 90 | Score | 69.1 |
| LiveBench JavaScript | 68.18 | Score | 69.1 |
| LiveBench Table Join | 49.1 | Score | 60.3 |
| LiveBench AMPS Hard | 98 | Score | 58.8 |
| LiveBench Simplify | 66.18 | Score | 58.8 |
| LiveBench Theory of Mind | 80.77 | Score | 58.1 |
| LiveBench TypeScript | 43.33 | Score | 55.9 |
| Last Translation Benchmark | 5.71 | Verified Translations (%) | 54.5 |
| LiveBench Consecutive Events | 80.53 | Score | 50 |
Interactive version: theaggregate.ai/model?slug=mistral-large-4-high · How It Works · Data refreshed daily, snapshot 2026-10-10.