GPT-6.2 Astra tops AA-Robotics v0.1 with 75% fewer arm commands than Claude
ArtificialAnlys · x · 2026-11-21
Artificial Analysis's AA-Robotics v0.1 results show GPT-6.2 Astra completing robot-arm tasks with the fewest moves of 11 models tested: 92 arm commands to clean up a box (75% fewer than Claude Fable 5.2) and 668 commands across six tasks, with the highest overall score.
Related event: GPT-6.2 Astra Tops New AA-Robotics Benchmark(2 posts)→
More from Embodied
- Reverse-engineering Apple Watch: a single Claude Code prompt builds a physics watch face in 30 minutes — mtizard · 2026-11-21
- Robotics Founder: Housekeeping Bots Should Target Mundane Upkeep, Not Party Tricks — Ben_Reinhardt · 2026-11-21
- Heave-Ho: decentralized framework coordinates teams of 2–10 humanoids on long-horizon tasks — yuewang314 · 2026-11-21
- USC's Heave-Ho coordinates humanoid robot teams with zero network messages, 86% success at 120x faster planning — yuewang314 · 2026-11-21
- Unitree G1 humanoid robot 'gets a job' at U-Haul in real-world demo — yuewang314 · 2026-11-21
- AgentRoboCritic: action-level benchmark reveals how frontier agents really control robots — XiongChenyan · 2026-11-21