GPT-5.6 Terra (max)

openai/gpt-5.6-terra

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	59	1951.42	$1.25405	$0.0006426	rating point	2026-07-09
Reason	ProofBench	24	0.71	$2.91861	$4.111	correct answer	2026-07-09
Agent	DeepSWE	1	0.351	$0.583249	$1.661	solved task	2026-07-09
Agent	DeepSWE	3	0.241	$0.427745	$1.778	solved task	2026-07-09
Agent	DeepSWE	5	0.538	$1.13438	$2.11	solved task	2026-07-09
Agent	DeepSWE	10	0.602	$2.12719	$3.535	solved task	2026-07-09
Agent	DeepSWE	22	0.696	$4.94585	$7.104	solved task	2026-07-09

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