WHAT NEW IN X11.03 TUE

AI collections from X · 22 collections · 65,263 posts

gpt-6IMAGE

GPT-6.1-sol beats Astra on planning tasks in hands-on test

The author found that while Astra ranked high in design reviews, it performed worse in execution, and GPT-6.1-sol (xhigh) was stronger for planning tasks.

jinjingliang
@JinjingLiangArchived 23 days agoOriginally posted 2026.10.09
GPT-6.1-sol beats Astra on planning tasks in hands-on test (image 1 of 2)
GPT-6.1-sol beats Astra on planning tasks in hands-on test (image 2 of 2)
jinjingliang @JinjingLiangOriginally posted 2026.10.09
Open original on X

GPT-6.1-sol (xhigh) > GPT-6-astra (high) for planning. Astra crushed the design review rankings in my previous post, but it seems like a worse doer 👀.

x.com/jinjingliang/status/2108382962740035590Archived 2026.10.10 10:03