Mistral AI·released 2026-10-061 source
Mistral Large 4 benchmark scores: 8 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 8 benchmarks·best result 98.33 on OTIS Mock AIME 2024-2025 (unverified)·0 of 8 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.33accuracy (%) | unverifiedT2 | 2026-10-06 |
| GPQA diamond | 84.09accuracy (%) | unverifiedT2 | 2026-10-06 |
| FrontierCode | 39.43accuracy (%) | unverifiedT1 | 2026-10-06https://cognition.com/frontiercode |
| Surface Evolver Bench | 28.12accuracy (%) | unverifiedT1 | 2026-10-06https://yhenon.github.io/surface-evolver-llm-eval/ |
| SimpleQA Verified | 20accuracy (%) | unverifiedT2 | 2026-10-06 |
| ProofBench | 10accuracy (%) | unverifiedT1 | 2026-10-06https://www.vals.ai/benchmarks/proof_bench |
| Mystery Game Puzzles | 8.57accuracy (%) | unverifiedT2 | 2026-10-06 |
| Furniture Assembly | 0accuracy (%) | unverifiedT2 | 2026-10-06 |
Claims drawn from cited facts, not live model generation.
This model comes from Mistral AI and was released in 2026. No parameter count is offered here, so its scale is best read through that provenance and recent vintage rather than a headline figure.
4 cited facts
This model is tracked across 8 benchmarks, but it holds no current top score on any of them. Its results remain unverified, meaning no outside evaluation has either confirmed or disputed the reported figures.
3 cited facts
On average it trails the benchmark leader by 48.86 points under the disclosed harness, a wide gap that reads as well behind the leaders rather than at the frontier or merely competitive. It holds the top score on zero benchmarks, so there is no genuine category leadership here yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Mistral Large 4 is an AI model developed by Mistral AI, released 2026-10-06. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Mistral Large 4 has recorded scores on 8 benchmarks, each shown with its evidence status.
Mistral Large 4 has recorded scores on 8 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, SimpleQA Verified, Mystery Game Puzzles, Surface Evolver Bench, ProofBench, and 2 more. The full table above shows each score with its evidence status.
0 of 8 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Mistral Large 4 has 8 tracked claims: 8 unverified.