Compare AI models

Specifications
Parameters
671B—
Context window
128k—
API pricing
Cheapest input
$0.50DeepInfra—
Cheapest output
$2.15DeepInfra—
$208DeepInfra · fp4—
Benchmarks
Humanity's Last Exam · with tools
17.7%44.4%
Overview
CompanyDeepSeekSpaceXSI
Release dateMay 28 2025Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 Heavy leads DeepSeek R1-0528 on 1 of the 1 benchmark they both report (Humanity's Last Exam). DeepSeek R1-0528 shipped 42 days before Grok 4 Heavy, so benchmark comparisons should account for the intervening progress.

DeepSeek R1-0528 is open weight, while Grok 4 Heavy is closed.

On Humanity's Last Exam · with tools, Grok 4 Heavy leads at 44.4% vs DeepSeek R1-0528 at 17.7%.