Compare AI models

Specifications
Parameters
24B253B
Context window
128k128k
Benchmarks
LiveCodeBench
70.88%66.3%
GPQA Diamond
70.07%76%
Overview
CompanyMistralNVIDIA
Release dateSep 17 2025Apr 7 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.2 and Llama Nemotron Ultra 253B are evenly matched across the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Llama Nemotron Ultra 253B shipped 163 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.

Magistral Small 1.2 has 24B parameters, while Llama Nemotron Ultra 253B has 253B. Context windows are 128k (Magistral Small 1.2) vs 128k (Llama Nemotron Ultra 253B).

On LiveCodeBench, Magistral Small 1.2 leads at 70.88% vs Llama Nemotron Ultra 253B at 66.3%. On GPQA Diamond, Llama Nemotron Ultra 253B leads at 76% vs Magistral Small 1.2 at 70.07%.