# LeVERB-Bench

From the catalogue. Listed by one researcher from one source page.

- id: `leverb-bench`
- kind: synthetic or generated
- robot or device: simulated humanoid whole-body control with vision and language (class: simulation)
- how collected: simulation benchmark
- size as stated: over 150 tasks, 10 categories
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2025
- organisation: Haoru Xue et al.
- licence: not stated (class: not stated)
- access: not stated (class: not stated)
- link (paper): https://arxiv.org/abs/2506.13751
- note: Sim-to-real-ready vision language benchmark.

Confirm the licence at the link before relying on it.