Benchmark Radar™
Star —

K9-Bench

Explore score history ↗

K9-Bench is a benchmark focused on real-world domestic dog videos, with approximately 5,000 question-answer pairs across 907 videos spanning 5 task categories. The tasks test long-form, canine-centric multimodal reasoning, including action and interaction understanding. A VLM/LLM-powered pipeline was used for data generation.

Released
2026-07-02
Evaluates
Multimodal, Reasoning, Robotics & Embodied AI
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

K9-Bench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite K9-Bench?

Related Multimodal, Reasoning, Robotics & Embodied AI benchmarks