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.
More from Models
- Indie dev's model scans raw binaries directly, scoring 0.977 on code blocks — wavefnx · 2026-11-18
- Insider claims Gemini closed the CUA gap to 0.9% with OpenAI on Agents' Last Exam — allenainie · 2026-11-18
- OpenAI engineers secretly use Astra for Law to write PRDs and design docs — sherwinwu · 2026-11-18
- Astra 6.2 is likely an improved checkpoint, not Bel — insider speculates Bel lands as 6.5 — haider1 · 2026-11-18
- Microsoft launches seven MAI models at Ignite, matching GPT-6 quality for under 2% of the cost — marlene_zw · 2026-11-18
- mitsuhiko on GPT-6.2 Astra/Sol: 'feel whelmed' after trying both — mitsuhiko · 2026-11-18