Compare AI models

Specifications
Parameters
671B4B
Context window
128k128k
API pricing
Cheapest input
$0.259SiliconFlow—
Cheapest output
$0.38DeepInfra—
$71.00DeepInfra · fp4—
Benchmarks
AIME 2025
93.1%46.3%
GPQA Diamond
82.4%55.1%
Overview
CompanyDeepSeekNVIDIA
Release dateDec 1 2025May 20 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2 leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Llama Nemotron Nano 4B v1.1 shipped 195 days before DeepSeek-V3.2, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2 has 671B parameters, while Llama Nemotron Nano 4B v1.1 has 4B. Context windows are 128k (DeepSeek-V3.2) vs 128k (Llama Nemotron Nano 4B v1.1).

On AIME 2025, DeepSeek-V3.2 leads at 93.1% vs Llama Nemotron Nano 4B v1.1 at 46.3%. On GPQA Diamond, DeepSeek-V3.2 leads at 82.4% vs Llama Nemotron Nano 4B v1.1 at 55.1%.