Compare AI models

Specifications
Parameters
671B51B
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
MMLU
88.5%80.2%
Overview
CompanyDeepSeekNVIDIA
Release dateDec 26 2024Sep 23 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Llama 3.1 Nemotron 51B on 1 of the 1 benchmark they both report (MMLU). Llama 3.1 Nemotron 51B shipped 94 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Llama 3.1 Nemotron 51B has 51B. Context windows are 128k (DeepSeek V3) vs 128k (Llama 3.1 Nemotron 51B).

On MMLU, DeepSeek V3 leads at 88.5% vs Llama 3.1 Nemotron 51B at 80.2%.