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.
More from Models
- 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
- Google insider: Gemini CUA now just 0.9% behind OpenAI's just-released model — allenainie · 2026-11-18
- mitsuhiko on GPT-6.2 Astra/Sol: 'feel whelmed' after trying both — mitsuhiko · 2026-11-18
- GPT-6.2 Astra/Sol panned: more hallucinations, slower, 'worst OpenAI model ever' — MicahBerkley · 2026-11-18