Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
Benchmarks
SWE-Bench Verified
49.2%61.6%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Jul 10 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Devstral Medium leads DeepSeek R1 on 1 of the 1 benchmark they both report (SWE-Bench Verified). DeepSeek R1 shipped 171 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 128k (Devstral Medium). DeepSeek R1 is open weight, while Devstral Medium is closed.

On SWE-Bench Verified, Devstral Medium leads at 61.6% vs DeepSeek R1 at 49.2%.