Compare AI models

Specifications
Parameters
24B30B
Context window
128k1M
API pricing
Cheapest input
—$0.06Nebius
Cheapest output
—$0.24Nebius
—$24.00Nebius · fp8
Benchmarks
LiveCodeBench
70.88%68.3%
GPQA Diamond
70.07%73%
Overview
CompanyMistralNVIDIA
Release dateSep 17 2025Dec 15 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.2 and Nemotron 3 Nano are evenly matched across the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Magistral Small 1.2 shipped 89 days before Nemotron 3 Nano, so benchmark comparisons should account for the intervening progress.

Magistral Small 1.2 has 24B parameters, while Nemotron 3 Nano has 30B. Context windows are 128k (Magistral Small 1.2) vs 1M (Nemotron 3 Nano).

On LiveCodeBench, Magistral Small 1.2 leads at 70.88% vs Nemotron 3 Nano at 68.3%. On GPQA Diamond, Nemotron 3 Nano leads at 73% vs Magistral Small 1.2 at 70.07%.