Compare AI models

Specifications
Parameters
24B—
Context window
40k128k
Benchmarks
AIME 2024
70.52%36.7%
GPQA Diamond
65.78%69.5%
Overview
CompanyMistralOpenAI
Release dateJul 24 2025Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.1 and GPT-4.5 are evenly matched across the 2 benchmarks they both report (AIME 2024, GPQA Diamond). GPT-4.5 shipped 147 days before Magistral Small 1.1, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Small 1.1) vs 128k (GPT-4.5). Magistral Small 1.1 is open weight, while GPT-4.5 is closed.

On AIME 2024, Magistral Small 1.1 leads at 70.52% vs GPT-4.5 at 36.7%. On GPQA Diamond, GPT-4.5 leads at 69.5% vs Magistral Small 1.1 at 65.78%.