OPENAI · MODEL TELEMETRY CARD

gpt-oss-20b

Canonical UID: openai/gpt-oss-20b · Released: 2025-08-05

Measured configurations of **gpt-oss-20b** 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	STD	#22 / 94	#79 / 94	566.05	$0.000717	$0.000001267	rating point

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