Compare AI models

Specifications
Parameters
24B—
Context window
128k128k
These models have no shared benchmark scores.
Overview
CompanyMistralOpenAI
Release dateSep 17 2025Feb 12 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.2 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 Small 1.2 shipped 148 days before GPT-5.3-Codex-Spark, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Small 1.2) vs 128k (GPT-5.3-Codex-Spark). Magistral Small 1.2 is open weight, while GPT-5.3-Codex-Spark is closed.

Direct benchmark comparisons are unavailable — Magistral Small 1.2 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks.