Back

Mistral

Devstral Small (May '25)

Open weights
Intelligence
8.7
Rank 478 of 744 measured models
Context window
256K
Rank 518 of 1199 measured models

Devstral Small (May '25) scores 8.7 on the Artificial Analysis Intelligence Index, ranking 478th of 744 measured models. The closest models on this index are Claude 3 Opus (8.7), Gemini 2.0 Pro Experimental (Feb '25) (8.7), and Nova 2.0 Lite (8.7).

Artificial Analysis Indices
Intelligence8.7
Rank 478 of 744 measured models
Standard Benchmarks
MMLU Pro63.2%
Rank 264 of 349 measured models
GPQA Diamond43.4%
Rank 503 of 619 measured models
HLE4.0%
Rank 580 of 664 measured models
LiveCodeBench25.8%
Rank 250 of 343 measured models
MATH-50068.4%
Rank 150 of 202 measured models
AIME 20246.7%
Rank 147 of 194 measured models
IFBench31.6%
Rank 371 of 450 measured models
AA-LCR32.0%
Rank 400 of 575 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