Google insider: Gemini CUA now just 0.9% behind OpenAI's just-released model

allenainie · x · 2026-11-18

A Google employee claims Gemini has closed the CUA (computer-use agent) gap with OpenAI — from 6 months behind, to 3, to just 0.9% versus OpenAI's just-released model.

The attached Agents' Last Exam v1.1 chart (long-horizon professional workflows) shows GPT-6.2 Astra leading at 78.3% with Gemini 4 Carbon at 77.4%; Claude Fable 5.2 scores high but costs $60 per task, while GPT-6.2 Astra tops the leaderboard in the $1-2 cost band.

Original post →

More from Models

Models channel →