WHAT NEW IN X11.05 THU

AI collections from X · 22 collections · 67,905 posts

gemini-4VIDEO

New benchmarks: nanoannot-1 beats Gemini 4 Argon at 1/10 cost

A team released MicroPlanBench and MicroAnnotationBench, claiming its nanoannot-1 beats Gemini 4 Argon on long-clip annotation at one-tenth the cost.

Bercan
@bercankilicArchived 15 days agoOriginally posted 2026.10.20
Bercan @bercankilicOriginally posted 2026.10.20
Open original on X

Today we are releasing two new benchmarks: MicroPlanBench (next-action prediction): GPT-6 Astra and GPT-6.1 Sol lead. Sol costs 1/5 as much. MicroAnnotationBench (labels + timing on long real-world clips): our nanoannot-1 beats Gemini 4 Argon, at 1/10 the cost.

x.com/bercankilic/status/2112316584534388884Archived 2026.10.20 09:56