Magistral Medium 1

by Mistral

Released · 20 days after Devstral Small (May '25)

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Intelligence Index12.5
Math Index40.3
Reasoning & knowledge
MMLU-Pro
75%
GPQA Diamond
68%
Humanity's Last Exam
10%
Long-context reasoning
0%
Coding
LiveCodeBench
53%
SciCode
30%
Agentic & tool use
Terminal-Bench Hard
9%
τ²-Bench Telecom
23%
Math & instruction following
AIME 2025
40%
IFBench
25%

Available routes

No routes currently available — Magistral Medium 1 isn't routed through the Opper gateway right now. It's tracked here for its release history.

Contact us about this model →

Available models from Mistral

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation