WHAT NEW IN X11.04 WED

AI collections from X · 22 collections · 66,612 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 18 hours ago
gpt-6VIDEO

Astra and Claude Fable 5.1 compared on robot manipulation tasks

Across eight manipulation tasks on Pandroid robots, GPT-6 Astra completed 35% of attempts and Claude Fable 5.1 completed 15% (p≈0.001), while human teleoperators completed every task.

Pantograph
@pantographPBCArchived 2026.09.18Originally posted 2026.09.18
Pantograph @pantographPBCOriginally posted 2026.09.18
Open original on X

Astra outperforms Fable at robotic control! We ran a controlled benchmark of GPT-6 Astra and Claude Fable 5.1 on our Pandroid robots across eight manipulation tasks. Astra completed 35% of attempts, Fable 15% (p≈0.001). Human teleoperators completed every task.

x.com/pantographpbc/status/2100628031731798186Archived 2026.09.18 10:09
Open original on X