Compare AI models

Specifications
Context window
200k128k
Benchmarks
SWE-Bench Verified
72.7%61.6%
Overview
CompanyAnthropicMistral
Release dateMay 22 2025Jul 10 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude Sonnet 4 leads Devstral Medium on 1 of the 1 benchmark they both report (SWE-Bench Verified). Claude Sonnet 4 shipped 49 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Sonnet 4) vs 128k (Devstral Medium).

On SWE-Bench Verified, Claude Sonnet 4 leads at 72.7% vs Devstral Medium at 61.6%.