Compare AI models

Specifications
Parameters
236B—
Context window
128k1M
Benchmarks
LiveCodeBench
39.7%57%
Overview
CompanyDeepSeekSpaceXSI
Release dateJul 24 2024Feb 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 3 leads DeepSeek Coder V2-0724 on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek Coder V2-0724 shipped 208 days before Grok 3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 1M (Grok 3). DeepSeek Coder V2-0724 is open weight, while Grok 3 is closed.

On LiveCodeBench, Grok 3 leads at 57% vs DeepSeek Coder V2-0724 at 39.7%.