gpt-oss-20b

Training compute

5.5×10²³ FLOP

Parameters

20.9B

Published

Aug 5, 2025

gpt-oss-20b is an AI model developed by OpenAI (United States), first published in August 2025. It works in the language domain, on tasks such as language modeling/generation and question answering.

Training it took an estimated 5.5×10²³ FLOP of compute (estimation method: hardware). The model has 20,910,000,000 parameters. Training ran on NVIDIA H100 SXM5 80GB.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering
Training compute: 5.5×10²³ FLOP
Compute estimation method: Hardware
Parameters: 20,910,000,000
Training hardware: NVIDIA H100 SXM5 80GB
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident

Benchmark results

01	ALE Bench	Performance	566
02	Terminal-Bench	Accuracy mean	0.03