‹ PublicAI Index
The LLM benchmark aggregator.
Mistral Large 2.1
Mistral
Strongest in Factual grounding (#9 of 104), weakest in Human preference (#226 of 354). Above par in 4 of 14 scopes. Among the models it meets almost everywhere, it finishes behind O3 and Muse Spark 1.1 and ahead of Mistral Medium 3.5 and Magistral Medium 1.2.
§ 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.
Safety54.3−7.1#67/3291/3
Factual grounding63.8−6.9#9/1041/1
Agents50.2−16.2#122/2981/6
Tool use50.4−23.6#34/811/1
Professional47.4−15#130/1941/2
Medical46.1−20.4#111/1491/1
Finance45.8−16.6#121/1621/1
Knowledge44−18.5#159/1971/3
Academic knowledge35.6−28.3#107/1231/1
Reasoning36−29.4#185/1951/5
Science30.3−33.2#111/1221/1
Mathematics34.8−29#142/1521/2
Human preference47.6−21.2#226/3541/1
Human preference47.6−21.2#226/3541/1
§ 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 Large 2.1, left for the other.
§ 3 · Sources
Where the numbers come from
4 publications, 8 figures. Every one links to the page it was read from.
LMArena Text 1306
BFCL v4 38.37%
Vals · TaxEval 63.78%Vals · MedQA 76.22%Vals · GPQA Diamond 47.73%Vals · MMLU Pro 69.71%Vals · AIME 9.17%
Vectara · Factual consistency 95.5%
Badge
[](https://publicai.io/model-index/m/mistral-large-2-1)