Mistral AI·released 2025-03-171 source
Mistral Small 3.1 benchmark scores: 5 benchmarks tracked. 20% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 46.77 on MATH level 5 (reproduced)·1 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 46.77accuracy (%) | reproduced· optimizedT1 | 2025-03-17Epoch AI |
| DTBench | 31.07accuracy (%) | unverifiedT1 | 2025-03-17https://conceptualreasoning.ai/dtbench |
| GPQA diamond | 29.97accuracy (%) | unverifiedT2 | 2025-03-17 |
| OTIS Mock AIME 2024-2025 | 5.74accuracy (%) | unverifiedT2 | 2025-03-17 |
| Chess Puzzles | 0accuracy (%) | unverifiedT2 | 2025-03-17 |
Claims drawn from cited facts, not live model generation.
This model originates from Mistral AI and was released in 2025. That recent vintage and independent European pedigree mean it reflects current training and architecture practice from its developer rather than a legacy design.
4 cited facts
This model is scored on 5 tracked benchmarks, but holds no current top score. Its results are independently reproduced by outside evaluation, so the record can be trusted as verified.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 70.13 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Mistral Small 3.1 is an AI model developed by Mistral AI, released 2025-03-17. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Mistral Small 3.1 has recorded scores on 5 benchmarks, each shown with its evidence status.
Mistral Small 3.1 has recorded scores on 5 benchmarks — GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, DTBench, Chess Puzzles. The full table above shows each score with its evidence status.
1 of 5 recorded scores (20%) are independently reproduced rather than self-reported by the lab.
Mistral Small 3.1 has 5 tracked claims: 1 independently reproduced, 4 unverified.