Claude Opus 5 (high)

anthropic/claude-opus-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	64	2164.57	$1.89051	$0.0008734	rating point	2026-07-24
Reason	ProofBench	17	0.78	$2.10619	$2.7	correct answer	2026-07-24
Agent	DeepSWE	8	0.581	$1.66262	$2.86	solved task	2026-07-24
Agent	DeepSWE	15	0.689	$3.28979	$4.774	solved task	2026-07-24
Agent	DeepSWE	27	0.728	$6.07608	$8.343	solved task	2026-07-24
Agent	DeepSWE	33	0.732	$9.0722	$12.4	solved task	2026-07-24
Agent	DeepSWE	37	0.736	$11.8376	$16.07	solved task	2026-07-24

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