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)→

Original post →

More from Embodied

Embodied channel →