Compare AI models

Specifications
Parameters
24B9B/32B
Context window
40k128k
Benchmarks
LiveCodeBench
55.84%59.1%
AIME 2024
70.68%80.8%
AIME 2025
62.76%63.6%
Overview
CompanyMistralZ.ai
Release dateJun 10 2025Apr 14 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

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

Magistral Small has 24B parameters, while GLM-Z1-0414 has 9B/32B. Context windows are 40k (Magistral Small) vs 128k (GLM-Z1-0414).

On LiveCodeBench, GLM-Z1-0414 leads at 59.1% vs Magistral Small at 55.84%. On AIME 2024, GLM-Z1-0414 leads at 80.8% vs Magistral Small at 70.68%. On AIME 2025, GLM-Z1-0414 leads at 63.6% vs Magistral Small at 62.76%.