Back

Mistral

Devstral Medium

Closed weightsModels.dev
Intelligence
9.0
Rank 462 of 744 measured models
Context window
256K
Rank 518 of 1199 measured models

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

Artificial Analysis Indices
Intelligence9.0
Rank 462 of 744 measured models
Math4.7
Rank 249 of 270 measured models
Standard Benchmarks
MMLU Pro70.8%
Rank 218 of 349 measured models
GPQA Diamond49.2%
Rank 476 of 619 measured models
HLE3.8%
Rank 593 of 664 measured models
LiveCodeBench33.7%
Rank 204 of 343 measured models
MATH-50070.7%
Rank 139 of 202 measured models
AIME 20246.7%
Rank 147 of 194 measured models
AIME 20254.7%
Rank 249 of 270 measured models
IFBench29.9%
Rank 387 of 450 measured models
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