Compare AI models

Specifications
Parameters
24B—
Context window
128k128k
Benchmarks
GPQA Diamond
70.07%42.5%
Overview
CompanyMistralOpenAI
Release dateSep 17 2025Nov 6 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.2 leads GPT-4 Turbo on 1 of the 1 benchmark they both report (GPQA Diamond). GPT-4 Turbo shipped 681 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Small 1.2) vs 128k (GPT-4 Turbo). Magistral Small 1.2 is open weight, while GPT-4 Turbo is closed.

On GPQA Diamond, Magistral Small 1.2 leads at 70.07% vs GPT-4 Turbo at 42.5%.