Compare AI models

Specifications
Context window
2M128k
Benchmarks
LiveCodeBench
34.3%75%
GPQA Diamond
59.1%76.26%
Overview
CompanyGoogleMistral
Release dateSep 24 2024Sep 17 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.2 leads Gemini 1.5 Pro-002 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Gemini 1.5 Pro-002 shipped 358 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 2M (Gemini 1.5 Pro-002) vs 128k (Magistral Medium 1.2).

On LiveCodeBench, Magistral Medium 1.2 leads at 75% vs Gemini 1.5 Pro-002 at 34.3%. On GPQA Diamond, Magistral Medium 1.2 leads at 76.26% vs Gemini 1.5 Pro-002 at 59.1%.