Compare AI models

Specifications
Parameters
671B8B
Context window
128k4k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
MMLU
88.5%54.4%
Overview
CompanyDeepSeekNVIDIA
Release dateDec 26 2024Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Nemotron-3 8B on 1 of the 1 benchmark they both report (MMLU). Nemotron-3 8B shipped 407 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Nemotron-3 8B has 8B. Context windows are 128k (DeepSeek V3) vs 4k (Nemotron-3 8B).

On MMLU, DeepSeek V3 leads at 88.5% vs Nemotron-3 8B at 54.4%.