WOVEN Benchmark

What is WOVEN?

Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. Benchmark Radar tracks WOVEN, cited by 1 source…

Released

2026-10-08

Evaluates

Multimodal, Reasoning, Robotics & Embodied AI

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2610.12417

WOVEN paper

• Paper https://arxiv.org/abs/2610.12417

Which sources cite WOVEN?

• WOVEN

Related Multimodal, Reasoning, Robotics & Embodied AI benchmarks

• 2d-fet-bench
• 360CityArena
• 3DCodeBench
• 4DSynth-Nav
• A-Bench
• A-OKVQA
• ABC-Bench
• ACG-Bench