ActionLens Benchmark

What is ActionLens?

Video-capable vision-language models score above 80\% on popular benchmarks yet struggle with spatial-temporal binding: associating the right action with the…

Released

2026-09-28

Evaluates

General AI, Multimodal, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.34547

ActionLens paper

• Paper https://arxiv.org/abs/2609.34547
• Website https://anonymous.4open.science/r/lmms-eval-2276

Which sources cite ActionLens?

• ActionLens

Related General AI, Multimodal, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A-Bench
• A-OKVQA
• A3S-Bench