Compare AI models

Specifications
Parameters
236B—
Context window
128k128k
Benchmarks
HumanEval
87.2%83.7%
Overview
CompanyDeepSeekOpenAI
Release dateJul 24 2024Nov 6 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads GPT-4 Turbo on 1 of the 1 benchmark they both report (HumanEval). GPT-4 Turbo shipped 261 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 128k (GPT-4 Turbo). DeepSeek Coder V2-0724 is open weight, while GPT-4 Turbo is closed.

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs GPT-4 Turbo at 83.7%.