WHAT NEW IN X11.03 TUE

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

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 22 hours ago
gpt-6IMAGE

RoboDojo-RC real-robot benchmark jumps from 15% to 43% in two months

The top score on the RoboDojo-RC Tier 1 real-robot benchmark rose from 15% to 43% in two months, with the best results set by GPT-5.6 Sol, Gemini 3.8 Flash and GPT-6 Astra.

Jay Chooi
@chooi_jeqArchived 25 days agoOriginally posted 2026.10.08
RoboDojo-RC real-robot benchmark jumps from 15% to 43% in two months
Jay Chooi @chooi_jeqOriginally posted 2026.10.08
Open original on X

The best LLM score on a real-robot benchmark, RoboDojo-RC Tier 1, rose from 15% to 43% in 2 months, with best scores set by GPT-5.6 Sol, Gemini 3.8 Flash, and GPT-6 Astra.

x.com/chooi_jeq/status/2107904980674060501Archived 2026.10.08 10:04
Open original on X