Benchmark Radar™
Star —

WatchAct Benchmark

Explore score history ↗

WatchAct evaluates robot manipulation from observed human behavior. Each instance pairs a human-action video and a language instruction with an aligned simulator scene and an executable LIBERO task. It covers 3,000 long-horizon instances across 14 tasks in four capability domains: Event Grounding, Procedural Reasoning, Implicit Intent Inference, and Episodic Reasoning. The evaluation protocol separately measures video-to-plan reasoning, policy execution under oracle plans, and full task completion, in simulation and on a Franka Research 3 robot.

Released
2026-06-24
Institutions
University of North Carolina at Chapel Hill
Evaluates
Robot manipulation, Robotics, Robotics & Embodied AI
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

WatchAct paper and code

No reported scores are on record for this benchmark yet.

Which sources cite WatchAct?

Related Robot manipulation, Robotics, Robotics & Embodied AI benchmarks