GPT-5.2 (medium)

openai/gpt-5.2-20251211

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	31	1249.83	$0.142947	$0.0001144	rating point	2025-12-11
Code	ALE-Bench	44	1293.55	$0.296865	$0.0002295	rating point	2025-12-11
Reason	ProofBench	32	0.15	$1.05969	$7.065	correct answer	2025-12-11

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