DunphyBench

What is DunphyBench?

DunphyBench evaluates long-horizon embodied decision-making in housing environments, requiring agents to navigate and choose options aligned with…

Released

2026-08-02

Evaluates

Agents, Multimodal, Robotics & Embodied AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.01456

DunphyBench paper

• Paper https://arxiv.org/abs/2608.01456

Which sources cite DunphyBench?

• DunphyBench

Related Agents, Multimodal, Robotics & Embodied AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 4DSynth-Nav
• A-Bench
• A-OKVQA
• A3S-Bench
• ABC-Bench