Mistral: Mistral Medium 3.5

mistralai/mistral-medium-3-5

88th smartest of 182ReasoningToolsJSONVision

Use via OpenRouter ↗

Intelligence

29.9

88th of 182

Design Elo

1166

Website

Speed

—

tokens/sec

Latency

—

first token

Input price

$1.50

257th cheapest

Context

262K

How it compares

Smarter than52%

of all ranked models

Cheaper than23%

of all ranked models

Overview

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...

Benchmarks

independent · Artificial Analysis & Design Arena

Artificial Analysis75th percentile

Intelligence Index

29.9

Coding Index

46.9

GPQA Diamond

75%

Humanity's Last Exam

13%

SciCode

40%

Tau²-Bench (agentic)

94%

Design Arena · Elo5,833 tournaments

Website

1166

Data Viz

1149

1118

svg

995

Providers & pricing (1)

Provider	In $/M	Out $/M	Context	Uptime
Mistral	$1.50	$7.50	262K	100%

Specifications

Context window262K

Max output—

Knowledge cutoff—

Input modalitiestext, image, file

Output modalitiestext

Prompt caching—

Cache read price—

ModeratedNo

Mistral Medium 3.5 FAQ

How much does Mistral Medium 3.5 cost?

Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens via OpenRouter, making it 257th cheapest of 332 paid models.

How smart is Mistral Medium 3.5?

Mistral Medium 3.5 scores 29.9 on the Artificial Analysis Intelligence Index, ranking 88th of 182 benchmarked models, with a GPQA Diamond score of 75%.