Compare AI models

Specifications
Parameters
236B314B
Context window
128k8k
Benchmarks
HumanEval
87.2%63.2%
Overview
CompanyDeepSeekSpaceXSI
Release dateJul 24 2024Nov 3 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Grok‑1 on 1 of the 1 benchmark they both report (HumanEval). Grok‑1 shipped 264 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Grok‑1 has 314B. Context windows are 128k (DeepSeek Coder V2-0724) vs 8k (Grok‑1).

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Grok‑1 at 63.2%.