SafeAgentBench

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

• id: safeagentbench
• kind: language and reasoning annotation
• robot or device: embodied task planning (class: simulation)
• how collected: curated tasks
• size as stated: 750 tasks
• hours: not stated | hours only claimed: none | episodes: not stated
• year: 2024
• organisation: not stated
• licence: not stated (class: not stated)
• access: not stated (class: not stated)
• link (paper): https://arxiv.org/abs/2412.13178

Confirm the licence at the link before relying on it.