Compare AI models

Specifications
Parameters
—24B
Context window
1M128k
Benchmarks
AIME 2025
95%77.34%
GPQA Diamond
91.9%70.07%
Overview
CompanyGoogleMistral
Release dateNov 18 2025Sep 17 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.0 Pro leads Magistral Small 1.2 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Magistral Small 1.2 shipped 62 days before Gemini 3.0 Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.0 Pro) vs 128k (Magistral Small 1.2). Gemini 3.0 Pro is closed, while Magistral Small 1.2 is open weight.

On AIME 2025, Gemini 3.0 Pro leads at 95% vs Magistral Small 1.2 at 77.34%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs Magistral Small 1.2 at 70.07%.