Compare AI models

Specifications
Parameters
671B—
Context window
128k256k
Benchmarks
LiveCodeBench
65.9%79%
GPQA Diamond
71.5%87.5%
Overview
CompanyDeepSeekSpaceXSI
Release dateJan 20 2025Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads DeepSeek R1 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek R1 shipped 170 days before Grok 4, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 256k (Grok 4). DeepSeek R1 is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Grok 4 leads at 87.5% vs DeepSeek R1 at 71.5%.