Compare AI models

Specifications
Parameters
236B—
Context window
128k256k
Benchmarks
LiveCodeBench
39.7%79%
Overview
CompanyDeepSeekSpaceXSI
Release dateJul 24 2024Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads DeepSeek Coder V2-0724 on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek Coder V2-0724 shipped 350 days before Grok 4, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 256k (Grok 4). DeepSeek Coder V2-0724 is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs DeepSeek Coder V2-0724 at 39.7%.