‹ PublicAI Index
The LLM benchmark aggregator.
Mistral Medium 3.1
Mistral
Strongest in Medical (#101 of 149), weakest in Safety (#303 of 327). Above par in 2 of 14 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 4.7 and Gemini 3.1 Pro and ahead of Command A and Llama 4 Maverick Instruct.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Human preference57.4−11.4#127/3541/1
Human preference57.4−11.4#127/3541/1
Reasoning45.8−19.6#131/1951/5
Mathematics43.6−20.2#113/1521/2
Knowledge46.9−15.6#143/1971/3
Academic knowledge42.6−21.3#102/1231/1
Professional41.9−20.5#176/1941/2
Medical47.2−19.3#101/1491/1
Finance39.7−22.7#139/1621/1
Legal37.6−28.3#158/1731/1
Agents44.3−22#233/2982/6
Knowledge work40.8−29.9#148/2082/2
Safety42.5−18.9#303/3271/3
Factual grounding26−44.7#101/1041/1
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Mistral Medium 3.1, left for the other.
§ 3 · Sources
Where the numbers come from
5 publications, 11 figures. Every one links to the page it was read from.
LMArena Text 1408
GDPval-AA 393
AA-Briefcase 531
Vals · LegalBench 61.98%Vals · CorpFin 50.74%Vals · TaxEval 70.32%Vals · MortgageTax 36.45%Vals · MedQA 78.23%Vals · MMLU Pro 75.29%Vals · AIME 42.29%
Vectara · Factual consistency 77.3%
Badge
[](https://publicai.io/model-index/m/mistral-medium-3-1)