Compare AI models

Specifications
Parameters
236B—
Context window
128k1M
Benchmarks
HumanEval
87.2%71.9%
Overview
CompanyDeepSeekGoogle
Release dateJul 24 2024Feb 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Gemini 1.5 Pro on 1 of the 1 benchmark they both report (HumanEval). Gemini 1.5 Pro shipped 160 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 1M (Gemini 1.5 Pro). DeepSeek Coder V2-0724 is open weight, while Gemini 1.5 Pro is closed.

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Gemini 1.5 Pro at 71.9%.