Compare AI models

Specifications
Parameters
4B—
Context window
256k128k
Benchmarks
MATH-500
95.4%87.1%
GPQA Diamond
53.2%69.5%
Overview
CompanyNVIDIAOpenAI
Release dateMar 16 2026Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Nano 4B and GPT-4.5 are evenly matched across the 2 benchmarks they both report (MATH-500, GPQA Diamond). GPT-4.5 shipped 382 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Nemotron 3 Nano 4B) vs 128k (GPT-4.5). Nemotron 3 Nano 4B is open weight, while GPT-4.5 is closed.

On MATH-500, Nemotron 3 Nano 4B leads at 95.4% vs GPT-4.5 at 87.1%. On GPQA Diamond, GPT-4.5 leads at 69.5% vs Nemotron 3 Nano 4B at 53.2%.