PlayWorld Benchmark

What is PlayWorld?

PlayWorld evaluates interactive video world models across 171 scenarios with long-horizon objectives. Agent players adaptively control each model, and…

Released

2026-08-13

Evaluates

Agents, General AI, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.13552

PlayWorld paper and code

• Paper https://arxiv.org/abs/2608.13552
• Code https://github.com/kxding/PlayWorld
• Website https://kxding.github.io/project/PlayWorld/

Which sources cite PlayWorld?

• PlayWorld

Related Agents, General AI, Vision & 3D benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision