Compare AI models

Specifications
Parameters
236B—
Context window
128k200k
Benchmarks
SWE-Bench Verified
19%49.3%
HumanEval
87.2%97.6%
Overview
CompanyDeepSeekOpenAI
Release dateJul 24 2024Jan 31 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

o3-mini-high leads DeepSeek Coder V2-0724 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, HumanEval). DeepSeek Coder V2-0724 shipped 191 days before o3-mini-high, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 200k (o3-mini-high). DeepSeek Coder V2-0724 is open weight, while o3-mini-high is closed.

On SWE-Bench Verified, o3-mini-high leads at 49.3% vs DeepSeek Coder V2-0724 at 19%. On HumanEval, o3-mini-high leads at 97.6% vs DeepSeek Coder V2-0724 at 87.2%.