Compare AI models

Specifications
Parameters
236B—
Context window
128k128k
Benchmarks
SWE-Bench Verified
19%38%
HumanEval
87.2%88.6%
Overview
CompanyDeepSeekOpenAI
Release dateJul 24 2024Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.5 leads DeepSeek Coder V2-0724 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, HumanEval). DeepSeek Coder V2-0724 shipped 218 days before GPT-4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 128k (GPT-4.5). DeepSeek Coder V2-0724 is open weight, while GPT-4.5 is closed.

On SWE-Bench Verified, GPT-4.5 leads at 38% vs DeepSeek Coder V2-0724 at 19%. On HumanEval, GPT-4.5 leads at 88.6% vs DeepSeek Coder V2-0724 at 87.2%.