Compare AI models

Benchmarks
Humanity's Last Exam · with tools
50.4%44.4%
Overview
CompanyMetaSpaceXSI
Release dateApr 8 2026Jul 9 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Muse Spark leads Grok 4 Heavy on 1 of the 1 benchmark they both report (Humanity's Last Exam). Grok 4 Heavy shipped 273 days before Muse Spark, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On Humanity's Last Exam · with tools, Muse Spark leads at 50.4% vs Grok 4 Heavy at 44.4%.