Compare AI models

Specifications
Context window
40k128k
These models have no shared benchmark scores.
Overview
CompanyMistralOpenAI
Release dateJul 24 2025Feb 12 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.1 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Magistral Medium 1.1 shipped 203 days before GPT-5.3-Codex-Spark, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Medium 1.1) vs 128k (GPT-5.3-Codex-Spark).

Direct benchmark comparisons are unavailable — Magistral Medium 1.1 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks.