Compare AI models

Specifications
Parameters
671B1B/3B/11B/90B
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra$0.027Cloudflare
Cheapest output
$0.712DeepInfra$0.201Cloudflare
$103StreamLake$15.45Cloudflare
Benchmarks
MMLU
88.5%86%
Overview
CompanyDeepSeekMeta
Release dateDec 26 2024Sep 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads LLaMA 3.2 on 1 of the 1 benchmark they both report (MMLU). LLaMA 3.2 shipped 92 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while LLaMA 3.2 has 1B/3B/11B/90B. Context windows are 128k (DeepSeek V3) vs 128k (LLaMA 3.2).

On MMLU, DeepSeek V3 leads at 88.5% vs LLaMA 3.2 at 86%.