Back

Mistral

Mistral Medium 3

Closed weightsModels.dev
Intelligence
9.0
Rank 462 of 744 measured models
Output speed
45.1 t/s
Rank 336 of 403 measured models
Price/1M
$0.80
Rank 340 of 659 measured models
Context window
128K
Rank 773 of 1199 measured models

Mistral Medium 3 scores 9.0 on the Artificial Analysis Intelligence Index, ranking 462nd of 744 measured models. The closest models on this index are Devstral Medium (9.0), GPT-4o (March 2025, chatgpt-4o-latest) (9.0), and Tri-21B-Think (9.0).

Artificial Analysis Indices
Intelligence9.0
Rank 462 of 744 measured models
Math30.3
Rank 185 of 270 measured models
Standard Benchmarks
MMLU Pro76.0%
Rank 168 of 349 measured models
GPQA Diamond57.8%
Rank 420 of 619 measured models
HLE4.1%
Rank 567 of 664 measured models
LiveCodeBench40.0%
Rank 182 of 343 measured models
MATH-50090.7%
Rank 70 of 202 measured models
AIME 202444.0%
Rank 66 of 194 measured models
AIME 202530.3%
Rank 185 of 270 measured models
IFBench39.3%
Rank 284 of 450 measured models
Additional benchmarks6
Design Arena · 3d54.7%
Design Arena · Codecategories48.1%
Design Arena · Dataviz46.0%
Design Arena · Gamedev45.2%
Design Arena · Uicomponent49.6%
Design Arena · Website47.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy