Kimi K3.1 Pro scores just 9% on real-robot tasks, trailing Opus 5.5 and Gemini 4 Argon
peterwildeford · x · 2026-10-24
Kimi K3.1 Pro scored only 9% on real-robot tasks, behind Opus 5.5, Gemini 4 Argon and GPT-6 Astra. Peter Wildeford quipped that the robot capabilities seemingly 'forgot to be distilled' into the model.
Related event: Kimi K3.1 Pro scores just 9% on real-robot tasks, lagging behind rivals(2 posts)→
More from Embodied
- The Intuition Test: No Human Could Master Finger-by-Finger Robot Control Through an LLM — adam_karvonen · 2026-10-24
- Researcher Bets GPT-7 Still Can't Install a Car Oil Pan: The LLM Robotics Skeptic Thread — MaskedTorah · 2026-10-24
- Multiple iPhone Duo foldable screens reported cracking along the crease — lipeng0820 · 2026-10-24
- AI-designed 3D-printed electric motor prototype hints at a real-life 'matter compiler' — TinfoilTricorn · 2026-10-24
- AGCO to pilot Agility Robotics' humanoid Digit at Kansas farm machinery plant in 2027 — CyberRobooo · 2026-10-24
- High Refractive Index Glass Hits 2.1 With 97% Transmittance, Raising Eyebrows for AR Optics — jwt0625 · 2026-10-24