Compare AI models

Specifications
Parameters
671B4B
Context window
128k256k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
AIME 2025
89.3%78.5%
GPQA Diamond
79.9%53.2%
Overview
CompanyDeepSeekNVIDIA
Release dateSep 29 2025Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.2 Exp leads Nemotron 3 Nano 4B on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). DeepSeek V3.2 Exp shipped 168 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.2 Exp has 671B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 128k (DeepSeek V3.2 Exp) vs 256k (Nemotron 3 Nano 4B).

On AIME 2025, DeepSeek V3.2 Exp leads at 89.3% vs Nemotron 3 Nano 4B at 78.5%. On GPQA Diamond, DeepSeek V3.2 Exp leads at 79.9% vs Nemotron 3 Nano 4B at 53.2%.