Compare AI models

Specifications
Context window
128k128k
Benchmarks
SWE-Bench Verified
61.6%38%
Overview
CompanyMistralOpenAI
Release dateJul 10 2025Feb 27 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Devstral Medium leads GPT-4.5 on 1 of the 1 benchmark they both report (SWE-Bench Verified). GPT-4.5 shipped 133 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Devstral Medium) vs 128k (GPT-4.5).

On SWE-Bench Verified, Devstral Medium leads at 61.6% vs GPT-4.5 at 38%.