Benchmark Radar™
Star —

HumanCLAW-Bench

Explore score history ↗

HumanCLAW-Bench evaluates how VLMs make embodied decisions. Its 1,218 humanoid find-navigate-interact episodes span 41 indoor scenes, and low-level motor execution is factored out. Models are scored by success rate.

Released
2026-07-29
Evaluates
Multimodal, Robotics & Embodied AI
Openness
unknown
Importer
Claire Radar
Review status
ai-reviewed

HumanCLAW-Bench paper

No reported scores are on record for this benchmark yet.

Which sources cite HumanCLAW-Bench?

Related Multimodal, Robotics & Embodied AI benchmarks