Manipulation · Door limited¶

Claude Code 2.1.283 + Claude Opus 5.5, reasoning medium (OpenRouter)

← Task page · All HumanoidBench tasks in this run

ⓘ Note: `spec()` placed the hand 0.31 m beyond the real one (a massless link's centre of mass; fixed since); taking it for the fingertip, the agent concluded its arms pass through the door and ended itself at 14 min with 16 resets left.

Model use: est. $4.07 at list price