Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
SWE-Bench Verified
42%41.4%
GPQA Diamond
59.1%73.3%
MMLU
88.5%90.8%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Sep 12 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

o1-preview leads DeepSeek V3 on 2 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, MMLU). o1-preview shipped 105 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 128k (o1-preview). DeepSeek V3 is open weight, while o1-preview is closed.

On SWE-Bench Verified, DeepSeek V3 leads at 42% vs o1-preview at 41.4%. On GPQA Diamond, o1-preview leads at 73.3% vs DeepSeek V3 at 59.1%. On MMLU, o1-preview leads at 90.8% vs DeepSeek V3 at 88.5%.