Grok 4 Heavy

Grok 4 Heavy ranks first on AIME 2025.

xAI Released July 10th, 2025 Family Grok 4 The lab's model card Compare with others

Benchmarks with a score

Ranked first, out of five or more models

In the top three

xAI Jul 2025

Closed weights Flagship

No Epoch Capabilities Index score yet

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score		Rank	Source
Humanity's Last Exam	44.4%		#57 of 154	Lab model card

Benchmark	Score	Rank	Source
AIME 2025	100%	#1 of 143	Lab model card
GPQA Diamond	88.4%	#47 of 302	Lab model card
HMMT 2025	96.7%	#10 of 54	Lab model card
IMO-ProofBench	23.3%	#9 of 20	Official leaderboard
USAMO 2025	61.9%	#1 of 2	Lab model card
FrontierMath Tier 4	2.08%	#41 of 55	Epoch AI run

The benchmarks the lab chose to headline, with the scores it gave.

Grok 4 Jul 9, 2025