Compare AI models

Specifications
Parameters
236B—
Context window
128k1M
Benchmarks
SWE-Bench Verified
19%9.6%
HumanEval
87.2%74.3%
Overview
CompanyDeepSeekGoogle
Release dateJul 24 2024May 14 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Gemini 1.5 Flash on 2 of the 2 benchmarks they both report (SWE-Bench Verified, HumanEval). Gemini 1.5 Flash shipped 71 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 Flash). DeepSeek Coder V2-0724 is open weight, while Gemini 1.5 Flash is closed.

On SWE-Bench Verified, DeepSeek Coder V2-0724 leads at 19% vs Gemini 1.5 Flash at 9.6%. On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Gemini 1.5 Flash at 74.3%.