Compare AI models

Specifications
Parameters
671B109B
Context window
128k10M
API pricing
Cheapest input
$0.256DeepInfra$0.08DeepInfra
Cheapest output
$0.712DeepInfra$0.24DeepInfra
$103StreamLake$35.00DeepInfra · fp8
Benchmarks
LiveCodeBench
40.5%32.8%
GPQA Diamond
59.1%57.2%
Overview
CompanyDeepSeekMeta
Release dateDec 26 2024Apr 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads LLaMA 4 Scout on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek V3 shipped 100 days before LLaMA 4 Scout, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while LLaMA 4 Scout has 109B. Context windows are 128k (DeepSeek V3) vs 10M (LLaMA 4 Scout).

On LiveCodeBench, DeepSeek V3 leads at 40.5% vs LLaMA 4 Scout at 32.8%. On GPQA Diamond, DeepSeek V3 leads at 59.1% vs LLaMA 4 Scout at 57.2%.