01Overview02Models03Rankings04Compare05Quiz06Guide

Model

Mistral Medium 3.5 NO.25

Efficient dense workhorse with a built-in coding agent.

CompareBack to the index

Mistral AI · Mistral · Balanced · Closed weights

Specification

Fig.01 — Mistral — Mistral AI

FRANCE

Context window
262Ktokens
Max output
66Ktokens
Input price
$1.50/ 1M
Output price
$7.50/ 1M
Cached input
$0.15/ 1M
Throughput
—
Class
Balanced
Modalities
Text, Image, Pdf
Weights
Closed
Knowledge cutoff
—
Released
Apr 2026

Overview

Mistral Medium 3.5 is a proprietary dense ~128B model tuned for the price/performance sweet spot, bundling instruction-following, reasoning, and an agentic coding assistant that can open PRs. It delivers frontier-adjacent quality on many enterprise tasks at a fraction of flagship cost, but its agentic coding — while genuinely useful — is not as robust over long sessions as Claude or GPT. A strong default for cost-conscious production deployments.

Strengths

  • Excellent price/performance for enterprise use
  • Built-in agentic coding assistant
  • Strong multilingual and writing
  • 256K context with vision + PDF input

Trade-offs

  • Closed weights (API-only)
  • High output token price relative to input
  • Long-session agentic reliability below the frontier
  • Not the top pick for hardest reasoning

Fit

Best for

  • Cost-efficient production assistants
  • Multilingual enterprise workloads
  • Moderate coding automation
  • Document + vision tasks

Not ideal for

  • Fully autonomous long coding agents
  • Frontier math competitions

Capabilities

Ten axes, normalized 0–100 and scored the same way across the whole catalog — so a 78 here means what a 78 means anywhere else on the bench.

Fig.02 — Capability radar

0 — 100

Reasoning
73
Coding
71
Math
71
Writing
77
Knowledge
78
Speed
74
Agentic
68
Vision
68
Multilingual
84
Long Context
76

Benchmarks

Public results, with independent third-party runs marked. Bars normalize percentages against 100 and Elo ratings against a 1500 ceiling.

Independent index

Artificial Analysis Intelligence Index

Composite of ~9–10 independent evals · Artificial Analysis

30/ 100

BenchmarkResult
Artificial Analysis Intelligence IndexIndependentGeneral · Artificial Analysis
30%
SWE-bench VerifiedIndependentCoding · SWE-bench
77.6%

Alternatives

Models in roughly the same class — the ones worth weighing against this record.

Compare side by side
01Mistral Large 3Mistral AIEurope's flagship open-weight MoE — a strong, cheap, multilingual generalist.02Qwen3.7-MaxAlibaba QwenAlibaba's proprietary agentic reasoning flagship with a 1M context.03GPT-5.4 miniOpenAILow-cost previous-generation OpenAI workhorse for standard routing.

Index

PreviousMistral Large 3NextMistral Small 4
All models/EDUCATION