OPENAI · MODEL TELEMETRY CARD

GPT-5.4 mini

Canonical UID: openai/gpt-5.4-mini-20260317 · Released: 2026-03-17

Measured configurations of **GPT-5.4 mini** across benchmark suites. Exact machine values in site.json and data dumps.
Domain	Benchmark	Effort / Mode	⚡ Value/Cost #	🏆 Performance #	Score	Task $	Unit Cost $	Unit
Code	ALE-Bench	HIGH	#75 / 94	#39 / 94	1188.58	$0.271408	$0.0002283	rating point
Reason	ProofBench	XHIGH	#37 / 62	#42 / 62	0.21	$0.249441	$1.188	correct answer

Compare against all models on ← #frontier Live Ranking Board · Fixed-capability cost half-life analysis on /methodology.