Compare AI models

Specifications
Parameters
—30B
Context window
128k1M
API pricing
Cheapest input
—$0.00Nvidia
Cheapest output
—$0.00Nvidia
—$11.00Darkbloom · int4
Benchmarks
GPQA Diamond
76.26%75.4%
Overview
CompanyMistralNVIDIA
Release dateSep 17 2025Aug 11 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.2 leads Nemotron 3.5 Lightning on 1 of the 1 benchmark they both report (GPQA Diamond). Magistral Medium 1.2 shipped 328 days before Nemotron 3.5 Lightning, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Medium 1.2) vs 1M (Nemotron 3.5 Lightning). Magistral Medium 1.2 is closed, while Nemotron 3.5 Lightning is open weight.

On GPQA Diamond, Magistral Medium 1.2 leads at 76.26% vs Nemotron 3.5 Lightning at 75.4%.