Compare AI models

Specifications
Context window
128k400k
These models have no shared benchmark scores.
Overview
CompanyMistralOpenAI
Release dateJul 10 2025Sep 15 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Devstral Medium and GPT-5-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Devstral Medium shipped 67 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Devstral Medium) vs 400k (GPT-5-Codex).

Direct benchmark comparisons are unavailable — Devstral Medium and GPT-5-Codex don't publish scores on any of the same benchmarks.