Mistral Large 4 Preview (High): benchmark results
Provider: Mistral. Released 2026-10-06. Access: API.
Aggregate Rating 1751 ± 14, rank #249 of 2201 rated models, from 71 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OTIS Mock AIME 2024-25 | 98.33 | Accuracy (%) | 90 |
| Vals AI Harvey Legal Agent Bench | 15.83 | Accuracy (%) | 88.1 |
| LiveBench Table Reformat | 100 | Score | 81.4 |
| LiveBench Math Comp | 97.06 | Score | 80 |
| Vals AI Harvey Legal Agent Bench v1.1 | 17.5 | Task Resolution (%) | 79.2 |
| Epoch AI - GPQA Diamond | 88.07 | Accuracy (%) | 77 |
| LiveBench Python | 60 | Score | 72.1 |
| Vals AI Vibe Code Bench | 78.4 | Accuracy (%) | 71.4 |
| LiveBench JavaScript | 68.18 | Score | 69.3 |
| LiveBench Integrals With Game | 90 | Score | 68.6 |
| DuelLab GameBench 2 - Reasoning Variants | 57.57 | GameBench2 normalized score (0–100) | 68.5 |
| FrontierMath - Tiers 1-3 (v2) | 58.6 | Accuracy (%, 285 private v2 problems) | 67.1 |
Interactive version: theaggregate.ai/model?slug=mistral-large-4-preview-high · How It Works · Data refreshed daily, snapshot 2026-11-12.