Compare AI models

Specifications
Parameters
671B—
Context window
128k200k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
GPQA Diamond
59.1%81.3%
MMLU
88.5%90.3%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Apr 16 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

o4-mini-high leads DeepSeek V3 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). DeepSeek V3 shipped 111 days before o4-mini-high, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 200k (o4-mini-high). DeepSeek V3 is open weight, while o4-mini-high is closed.

On GPQA Diamond, o4-mini-high leads at 81.3% vs DeepSeek V3 at 59.1%. On MMLU, o4-mini-high leads at 90.3% vs DeepSeek V3 at 88.5%.