First quantitative evidence: Claude and GPT now use GUIs as well as APIs

ysu_nlp · x · 2026-09-12

A shared benchmark post offers the first quantitative evidence that Claude and GPT models are rapidly progressing on computer-use agents: Fable 5.1 and GPT-6 Astra now operate GUIs as well as APIs, ending the "CUA tax," while Grok 4.6 degrades 71% on GUIs despite strong API performance.

Original post →

More from Models

Models channel →