Claude Fable 5.2 jumps to 75 on Artificial Analysis's embodied AI benchmark, becoming the first model to crack the measure-box task using only video.
Full article content could not be extracted automatically. Read the original below.
Anthropic's Claude Fable 5.2 Tops Robot Arm Benchmark With 29-Point Leap
Claude Fable 5.2 jumps to 75 on Artificial Analysis's embodied AI benchmark, becoming the first model to crack the measure-box task using only video.
Topics: