Compare AI models

Specifications
Parameters
236B—
Context window
128k8k
API pricing
Cheapest input
—$30.00Azure
Cheapest output
—$60.00Azure
—$9,000Azure
Benchmarks
HumanEval
87.2%67%
Overview
CompanyDeepSeekOpenAI
Release dateJul 24 2024Mar 14 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads GPT-4 on 1 of the 1 benchmark they both report (HumanEval). GPT-4 shipped 498 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 8k (GPT-4). DeepSeek Coder V2-0724 is open weight, while GPT-4 is closed.

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs GPT-4 at 67%.