Compare AI models

Specifications
Parameters
—49B
Context window
128k128k
Benchmarks
LiveCodeBench
75%73.58%
AIME 2024
91.82%87.5%
AIME 2025
83.48%82.71%
GPQA Diamond
76.26%71.97%
Overview
CompanyMistralNVIDIA
Release dateSep 17 2025Jul 25 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.2 leads Llama Nemotron Super 49B v1.5 on 4 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). Llama Nemotron Super 49B v1.5 shipped 54 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Medium 1.2) vs 128k (Llama Nemotron Super 49B v1.5). Magistral Medium 1.2 is closed, while Llama Nemotron Super 49B v1.5 is open weight.

On LiveCodeBench, Magistral Medium 1.2 leads at 75% vs Llama Nemotron Super 49B v1.5 at 73.58%. On AIME 2024, Magistral Medium 1.2 leads at 91.82% vs Llama Nemotron Super 49B v1.5 at 87.5%. On AIME 2025, Magistral Medium 1.2 leads at 83.48% vs Llama Nemotron Super 49B v1.5 at 82.71%. On GPQA Diamond, Magistral Medium 1.2 leads at 76.26% vs Llama Nemotron Super 49B v1.5 at 71.97%.