Back

Mistral

Devstral Small (Jul '25)

Open weightsModels.devHugging Face
Intelligence
7.6
Rank 527 of 744 measured models
Context window
256K
Rank 518 of 1199 measured models

Devstral Small (Jul '25) scores 7.6 on the Artificial Analysis Intelligence Index, ranking 527th of 744 measured models. The closest models on this index are Mistral Large 2 (Nov '24) (7.6), QwQ 32B-Preview (7.6), and Sonar Pro (7.6).

Artificial Analysis Indices
Intelligence7.6
Rank 527 of 744 measured models
Math29.3
Rank 188 of 270 measured models
Standard Benchmarks
MMLU Pro62.2%
Rank 266 of 349 measured models
GPQA Diamond41.4%
Rank 520 of 619 measured models
HLE3.8%
Rank 593 of 664 measured models
LiveCodeBench25.4%
Rank 251 of 343 measured models
MATH-50063.5%
Rank 157 of 202 measured models
AIME 20240.3%
Rank 180 of 194 measured models
AIME 202529.3%
Rank 188 of 270 measured models
IFBench34.6%
Rank 334 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