Compare AI models

Specifications
Context window
128k256k
Benchmarks
LiveCodeBench
75%79%
AIME 2025
83.48%91.7%
GPQA Diamond
76.26%87.5%
Overview
CompanyMistralSpaceXSI
Release dateSep 17 2025Jul 9 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads Magistral Medium 1.2 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Grok 4 shipped 70 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Medium 1.2) vs 256k (Grok 4).

On LiveCodeBench, Grok 4 leads at 79% vs Magistral Medium 1.2 at 75%. On AIME 2025, Grok 4 leads at 91.7% vs Magistral Medium 1.2 at 83.48%. On GPQA Diamond, Grok 4 leads at 87.5% vs Magistral Medium 1.2 at 76.26%.