Hm seems like they forgot to also distill the robot capabilities

2 people · 2 posts · first post Sat 04:43 UTC · latest 2h ago

hm seems like they forgot to also distill the robot capabilities (@peterwildeford)

All posts · 2, most important first

1. @peterwildeford policy · Sat 04:43 UTC
   hm seems like they forgot to also distill the robot capabilities
   Kimi K3.1 Pro scores 9% on real-robot tasks, behind Opus 5.5, Gemini 4 Argon and GPT-6 Astra. open on X
   10 likes · 2 reposts
2. @tim_hua_ research · Sat 05:37 UTC
   Makes sense; many such benchmarks!
   Kimi K3.1 Pro scores 9% on real-robot tasks, behind Opus 5.5, Gemini 4 Argon and GPT-6 Astra. open on X
   1 likes · 0 reposts