Grok 4.5 (high)

xai/grok-4.5

Every ranked configuration of this model. Rank is dollars per unit of score on that job, and the unit is the job's own — the `per` column names it, because a rating point and a solved task are not the same thing to divide by. Displayed values are rounded; exact values in site.json and the dumps.
job	benchmark	#	score	task $	ratio $	per	released
Code	ALE-Bench	33	1309.28	$0.176767	$0.000135	rating point	2026-07-08
Reason	ProofBench	8	0.3	$0.484548	$1.615	correct answer	2026-07-08
Agent	DeepSWE	12	0.538	$2.41575	$4.493	solved task	2026-07-08

These are the numbers on #frontier. How a fixed capability's cost falls over time is on /methodology.