‹ PublicAI Index
The LLM benchmark aggregator.
Magistral Medium 1.2
Mistral
Strongest in Mathematics (#60 of 152, on 1 of its 2 boards), weakest in Agents (#228 of 298). Above par in 2 of 11 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5.1 and Claude Opus 5 and ahead of Llama 4 Maverick Instruct and GPT-4o.
§ 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.
Reasoning49−16.4#105/1951/5
Mathematics54.6−9.2#60/1521/2
Science40.4−23.1#98/1221/1
Knowledge43.5−19#169/1971/3
Academic knowledge34.3−29.6#113/1231/1
Professional42.5−19.9#170/1941/2
Medical53.2−13.3#63/1491/1
Finance39.8−22.6#138/1621/1
Legal35−30.9#171/1731/1
Agents44.6−21.8#228/2981/6
Knowledge work39.2−31.5#158/2081/2
§ 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 Magistral Medium 1.2, left for the other.
§ 3 · Sources
Where the numbers come from
2 publications, 9 figures. Every one links to the page it was read from.
GDPval-AA 176
Vals · LegalBench 54.77%Vals · CorpFin 47.4%Vals · TaxEval 61.94%Vals · MortgageTax 51.87%Vals · MedQA 89.47%Vals · GPQA Diamond 62.37%Vals · MMLU Pro 68.66%Vals · AIME 83.54%
Badge
[](https://publicai.io/model-index/m/magistral-medium-1-2)