Compare AI models

Specifications
Parameters
4B—
Context window
256k200k
Benchmarks
MATH-500
95.4%98.2%
GPQA Diamond
53.2%81.3%
Overview
CompanyNVIDIAOpenAI
Release dateMar 16 2026Apr 16 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

o4-mini-high leads Nemotron 3 Nano 4B on 2 of the 2 benchmarks they both report (MATH-500, GPQA Diamond). o4-mini-high shipped 334 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Nemotron 3 Nano 4B) vs 200k (o4-mini-high). Nemotron 3 Nano 4B is open weight, while o4-mini-high is closed.

On MATH-500, o4-mini-high leads at 98.2% vs Nemotron 3 Nano 4B at 95.4%. On GPQA Diamond, o4-mini-high leads at 81.3% vs Nemotron 3 Nano 4B at 53.2%.