Compare AI models

Specifications
Parameters
671B30B
Context window
128k1M
API pricing
Cheapest input
$0.256DeepInfra$0.06Nebius
Cheapest output
$0.712DeepInfra$0.24Nebius
$103StreamLake$24.00Nebius · fp8
Benchmarks
LiveCodeBench
40.5%68.3%
GPQA Diamond
59.1%73%
Overview
CompanyDeepSeekNVIDIA
Release dateDec 26 2024Dec 15 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Nano leads DeepSeek V3 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek V3 shipped 354 days before Nemotron 3 Nano, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Nemotron 3 Nano has 30B. Context windows are 128k (DeepSeek V3) vs 1M (Nemotron 3 Nano).

On LiveCodeBench, Nemotron 3 Nano leads at 68.3% vs DeepSeek V3 at 40.5%. On GPQA Diamond, Nemotron 3 Nano leads at 73% vs DeepSeek V3 at 59.1%.