Artificial Analysis: Claude Fable 5.2 leads AA-Robotics v0.1 with 75

Artificial Analysis says Claude Fable 5.2 is the new leader on AA-Robotics v0.1, its benchmark of models controlling a robot arm. Fable 5.2 scores 75, ahead of GPT-6 Astra (69) and GPT-6.1 Sol (65).

Artificial Analysis says Fable 5.2 is the first model to score on the "measure box" task. It did so using only video, leaving the tape measure in the setup and using its markings as a scale to estimate the size of the box.

These are Artificial Analysis's own measurements.