Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
GPQA Diamond
59.1%42.5%
MMLU
88.5%84.7%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Nov 6 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads GPT-4 Turbo on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). GPT-4 Turbo shipped 416 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 128k (GPT-4 Turbo). DeepSeek V3 is open weight, while GPT-4 Turbo is closed.

On GPQA Diamond, DeepSeek V3 leads at 59.1% vs GPT-4 Turbo at 42.5%. On MMLU, DeepSeek V3 leads at 88.5% vs GPT-4 Turbo at 84.7%.