LegalBench ↗61.98 %
Mistral Medium 3.1 (05/2025) · LegalBench · Accuracy ↗
Mistral / MODEL EVIDENCE
Mistral Medium 3.1 (05/2025)
10 benchmarks · 11 observations · 11 sources
Scores at a glance
10 benchmarks · large dot: Mistral Medium 3.1 (05/2025); small dots: closest models where reported
CorpFin v2 ↗50.74 %
Mistral Medium 3.1 (05/2025) · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗36.45 %
Mistral Medium 3.1 (05/2025) · MortgageTax · Accuracy ↗
1 more reported result
70.32 % · Mistral Medium 3.1 (05/2025) · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedQA (USMLE) ↗78.23 %
Mistral Medium 3.1 (05/2025) · MedQA · Accuracy ↗
AIME 2024–2025 · Vals ↗42.29 %
Mistral Medium 3.1 (05/2025) · AIME · Accuracy ↗
MATH-500 ↗87 %
Mistral Medium 3.1 (05/2025) · MATH 500 · Accuracy ↗
MGSM (Multilingual GSM) ↗90.87 %
Mistral Medium 3.1 (05/2025) · MGSM · Accuracy ↗
MMLU-Pro ↗75.29 %
Mistral Medium 3.1 (05/2025) · MMLU Pro · Accuracy ↗
MMMU-Pro ↗62.97 %
Mistral Medium 3.1 (05/2025) · MMMU Pro · Accuracy ↗
LiveCodeBench ↗44.84 %
Mistral Medium 3.1 (05/2025) · LiveCodeBench · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Gemini 1.5 Pro (002) →Google
10 of 10 shared benchmark comparisons
9 of 10 shared benchmark comparisons
9 of 10 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 ↗
- 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 Medium 3.1 (05/2025)