Compare AI models

Specifications
Parameters
—4B
Context window
40k128k
Benchmarks
AIME 2025
64.95%46.3%
GPQA Diamond
70.83%55.1%
Overview
CompanyMistralNVIDIA
Release dateJun 10 2025May 20 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Medium leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Llama Nemotron Nano 4B v1.1 shipped 21 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Medium) vs 128k (Llama Nemotron Nano 4B v1.1). Magistral Medium is closed, while Llama Nemotron Nano 4B v1.1 is open weight.

On AIME 2025, Magistral Medium leads at 64.95% vs Llama Nemotron Nano 4B v1.1 at 46.3%. On GPQA Diamond, Magistral Medium leads at 70.83% vs Llama Nemotron Nano 4B v1.1 at 55.1%.