Compare AI models

Specifications
Parameters
236B—
Context window
128k128k
Benchmarks
HumanEval
87.2%74.1%
Overview
CompanyDeepSeekSpaceXSI
Release dateJul 24 2024Mar 28 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Grok‑1.5 on 1 of the 1 benchmark they both report (HumanEval). Grok‑1.5 shipped 118 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 (Grok‑1.5). DeepSeek Coder V2-0724 is open weight, while Grok‑1.5 is closed.

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Grok‑1.5 at 74.1%.