Compare AI models

Specifications
Parameters
4B21B
Context window
256k128k
API pricing
Cheapest input
—$0.018AkashML
Cheapest output
—$0.09AkashML
—$8.10Darkbloom · fp8
Benchmarks
AIME 2025
78.5%91.7%
GPQA Diamond
53.2%71.5%
Overview
CompanyNVIDIAOpenAI
Release dateMar 16 2026Aug 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-20b leads Nemotron 3 Nano 4B on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). gpt-oss-20b shipped 223 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Nano 4B has 4B parameters, while gpt-oss-20b has 21B. Context windows are 256k (Nemotron 3 Nano 4B) vs 128k (gpt-oss-20b).

On AIME 2025, gpt-oss-20b leads at 91.7% vs Nemotron 3 Nano 4B at 78.5%. On GPQA Diamond, gpt-oss-20b leads at 71.5% vs Nemotron 3 Nano 4B at 53.2%.