Compare AI models

Specifications
Parameters
—9B/32B
Context window
40k128k
Benchmarks
LiveCodeBench
59.36%59.1%
AIME 2024
73.59%80.8%
AIME 2025
64.95%63.6%
Overview
CompanyMistralZ.ai
Release dateJun 10 2025Apr 14 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Medium leads GLM-Z1-0414 on 2 of the 3 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025). GLM-Z1-0414 shipped 57 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Medium) vs 128k (GLM-Z1-0414). Magistral Medium is closed, while GLM-Z1-0414 is open weight.

On LiveCodeBench, Magistral Medium leads at 59.36% vs GLM-Z1-0414 at 59.1%. On AIME 2024, GLM-Z1-0414 leads at 80.8% vs Magistral Medium at 73.59%. On AIME 2025, Magistral Medium leads at 64.95% vs GLM-Z1-0414 at 63.6%.