PhysAI-Bench

What is PhysAI-Bench?

The benchmark evaluates action selection in UAV mission traces through multiple-choice decision instances derived from conversational data.

Released

2026-09-20

Evaluates

Language & Knowledge, Robotics & Embodied AI, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.23695

PhysAI-Bench paper and code

• Paper https://arxiv.org/abs/2609.23695
• Code https://github.com/maferrag/physai-bench

Which sources cite PhysAI-Bench?

• PhysAI-Bench

Related Language & Knowledge, Robotics & Embodied AI, cs.AI benchmarks

• 2d-fet-bench
• 360CityArena
• 4DSynth-Nav
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABACUS
• ABC-Bench