Mistral Medium 3.5
Mistral · 1 configuration
Intelligence14.2
Input / 1M$1.50
Output / 1M$7.50
Context256K
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 medium · Click a point to switch configuration
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
14.2 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
74.8 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
13.8 %SciCodeCode generation for scientific research problems.
40.2 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
50.6 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
94.2 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
68.8 %MMMU-ProMultimodal understanding of academic problems that include images.
64.9 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
24.7 %Specifications from the catalog
Inputtext, image, file
Outputtext
Tool callingYes
Structured outputYes
Speed165.4 tok/s
First token2.30 s
Maximum output209.7K
Catalog listing date2026-04-30