Mistral AI·released 2024-11-181 source
Mistral Large 2 (Nov 2024) benchmark scores: 5 benchmarks tracked. 80% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 50.28 on MATH level 5 (reproduced)·4 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 50.28accuracy (%) | reproduced· optimizedT1 | 2024-11-18Epoch AI |
| GPQA diamond | 35.1accuracy (%) | reproduced· optimizedT1 | 2024-11-18Epoch AI |
| DTBench | 34.7accuracy (%) | unverifiedT1 | 2024-11-18https://conceptualreasoning.ai/dtbench |
| OTIS Mock AIME 2024-2025 | 7.69accuracy (%) | reproduced· optimizedT1 | 2024-11-18Epoch AI |
| FrontierMath-2025-02-28-Private | 0.6accuracy (%) | reproduced· optimizedT1 | 2024-11-18Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by Mistral AI and released in 2024, placing it in a recent generation of language models.
2 cited facts
This model is scored on 5 tracked benchmarks, but it holds no current top score. The record is independently reproduced, meaning outside evaluation backs up the scores.
3 cited facts
On average the model trails the leading score by 65.97 points across its benchmarks, a wide margin under whatever harness produced those numbers; read plainly, that puts it well behind the leaders rather than at the frontier or merely competitive. Consistently, it holds the top score on 0 benchmarks, so there is no category on which it can be called genuine leadership at present.
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 2 (Nov 2024) is an AI model developed by Mistral AI, released 2024-11-18. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Mistral Large 2 (Nov 2024) has recorded scores on 5 benchmarks, each shown with its evidence status.
Mistral Large 2 (Nov 2024) has recorded scores on 5 benchmarks — GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, DTBench, FrontierMath-2025-02-28-Private. The full table above shows each score with its evidence status.
4 of 5 recorded scores (80%) are independently reproduced rather than self-reported by the lab.
Mistral Large 2 (Nov 2024) has 5 tracked claims: 4 independently reproduced, 1 unverified.