Skip to content
llmwaves

Mistral Medium 3.5

Mistral AI · released Apr 30, 2026

ProprietaryReasoningTool useStructured outputVision

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...

Specification

Context window
262K
Max output
210K
Knowledge cutoff
Not stated
Parameters
Undisclosed
Licence
Proprietary
Serving providers
1
Moderated
No
Uptime
100.0%

Intelligence

14.2

55th percentile

Coding

46.9

Coding Index

Agentic

7.0

Agentic Index

Output speed

113 t/s

Median across providers

Latency

449ms

Time to first token

Cost per task

$0.68

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • τ²-bench (Telecom)
    94.2%
  • GPQA Diamond
    74.8%
  • AA-LCR (long context)
    69.3%
  • IFBench
    68.8%
  • SciCode
    40.2%
  • Terminal-Bench Hard
    33.3%
  • Humanity's Last Exam
    13.8%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
τ²-bench (Telecom)94.2%
GPQA Diamond74.8%
AA-LCR (long context)69.3%
IFBench68.8%
SciCode40.2%
Terminal-Bench Hard33.3%
Humanity's Last Exam13.8%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
gpt-oss-20b (free)15.2
o115.2
GLM 4.7 Flash14.9
GLM 4.614.9
Mistral Medium 3.514.2
Ling-2.6-flash14.2
V3.1 Terminus13.9
Command A+13.1

Percentile among all indexed models

Intelligence55th
Coding54th
Agentic26th
Terminal work77th
Arena Elo35th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$1.5
Output / 1M tokens
$7.5
Cached input / 1M
Not offered
Blended 3:1
$3

One task, estimated

$0.68

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,144
Win rate
42.4%
Strongest at
Websites
Tournaments
5,825

Elo by category

Dot position on a 925–1,150 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
Websites114442.4%
Data visualisation112143.2%
Game development108238.6%
UI components108037.2%
3D scenes106138.3%
SVG94826.7%