Mistral Small 3.2
Mistral · 1 configuration
Intelligence8.2
Input / 1M$0.08
Output / 1M$0.20
Context128K
Tariff: Mistral · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 0 without both values
Selected: thinking default · Click a point to switch configuration
Efficient Mistral model for fast chat, extraction, and production assistants
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
8.2 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
50.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
4.3 %SciCodeCode generation for scientific research problems.
28.6 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
5.6 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
29.5 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
33.5 %MMMU-ProMultimodal understanding of academic problems that include images.
48.0 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
14.8 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputNot available
SpeedNot available
First tokenNot available
Maximum output16.4K
Catalog listing date2025-06-20