Compare AI models

Specifications
Parameters
—4B
Context window
128k256k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
MATH-500
91%95.4%
GPQA Diamond
57.1%53.2%
Overview
CompanyMistralNVIDIA
Release dateMay 7 2025Mar 16 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3 and Nemotron 3 Nano 4B are evenly matched across the 2 benchmarks they both report (MATH-500, GPQA Diamond). Mistral Medium 3 shipped 313 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 256k (Nemotron 3 Nano 4B). Mistral Medium 3 is closed, while Nemotron 3 Nano 4B is open weight.

On MATH-500, Nemotron 3 Nano 4B leads at 95.4% vs Mistral Medium 3 at 91%. On GPQA Diamond, Mistral Medium 3 leads at 57.1% vs Nemotron 3 Nano 4B at 53.2%.