Insider claims Gemini closed the CUA gap to 0.9% with OpenAI on Agents' Last Exam

allenainie · x · 2026-11-18

An account claiming to have worked on Gemini says it helped close the CUA (computer-use agent) gap: "neck-in-neck with OpenAI." The attached Agents' Last Exam v1.1 leaderboard shows Gemini 4 Carbon at 77.4%, just 0.9% behind the newly released GPT-6.2 Astra at 78.3% — down from 6 months behind, then 3 months. The chart also shows Claude Fable 5.2 costing $60 per task and Claude Opus 5.5 $15, while Google/OpenAI's newest models stay under a few dollars; a footnote notes Fable 5.2's score excludes nine tasks that used a fallback model. The insider claim is unverified, but the leaderboard data is substantive.

Original post →

More from Models

Models channel →