LegalBench ↗69.16 %
Mistral Small 3.1 (03/2025) · LegalBench · Accuracy ↗
Mistral / MODEL EVIDENCE
Mistral Small 3.1 (03/2025)
11 benchmarks · 12 observations · 12 sources
Scores at a glance
11 benchmarks · large dot: Mistral Small 3.1 (03/2025); small dots: closest models where reported
CorpFin v2 ↗44.17 %
Mistral Small 3.1 (03/2025) · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗61.21 %
Mistral Small 3.1 (03/2025) · MortgageTax · Accuracy ↗
1 more reported result
58.3 % · Mistral Small 3.1 (03/2025) · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedQA (USMLE) ↗69.1 %
Mistral Small 3.1 (03/2025) · MedQA · Accuracy ↗
AIME 2024–2025 · Vals ↗3.54 %
Mistral Small 3.1 (03/2025) · AIME · Accuracy ↗
MATH-500 ↗68.4 %
Mistral Small 3.1 (03/2025) · MATH 500 · Accuracy ↗
MGSM (Multilingual GSM) ↗84.22 %
Mistral Small 3.1 (03/2025) · MGSM · Accuracy ↗
GPQA Diamond ↗44.19 %
Mistral Small 3.1 (03/2025) · GPQA Diamond · Accuracy ↗
MMLU-Pro ↗66.02 %
Mistral Small 3.1 (03/2025) · MMLU Pro · Accuracy ↗
MMMU-Pro ↗60.08 %
Mistral Small 3.1 (03/2025) · MMMU Pro · Accuracy ↗
LiveCodeBench ↗31.82 %
Mistral Small 3.1 (03/2025) · LiveCodeBench · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Mistral Small (02/2024) →Mistral
7 of 11 shared benchmark comparisons
Claude 3.5 Haiku Latest →Anthropic
8 of 11 shared benchmark comparisons
9 of 11 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- AIME — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- GPQA Diamond — evaluation methodology and results ↗
- LiveCodeBench — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- MATH 500 — evaluation methodology and results ↗
- MedQA — evaluation methodology and results ↗
- MGSM — evaluation methodology and results ↗
- MMLU Pro — evaluation methodology and results ↗
- MMMU Pro — evaluation methodology and results ↗
- MortgageTax — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
Names used in source tables
Mistral Small 3.1 (03/2025)