A wooden stick repeatedly taps a fabric sofa cushion. Each impact produces a soft dull thud with no ringing.
Seedance 2.0ByteDance · proprietary
Kling 3.0 OmniKuaishou · proprietary
Veo 3.1Google · proprietary
LTX-2.3Lightricks · open
Ovi 1.1character.ai · open
JavisDiT++JavisDiT · open
MagiHumanGAIR-NLP · open
Per-prompt rubric
Basic standards
Visual presence
- a wooden stick
- a fabric sofa cushion
Event: a stick taps a cushion
Audio presence
- a wooden stick
- a fabric sofa cushion
Sound: stick-on-cushion tap
Key standards
Visual physical commonsense (V-PC)
- A wooden stick visibly taps the fabric cushion, with the cushion visibly compressing on each contact.
Audio physical commonsense (A-PC)
- Each impact is a soft dull thud with rapid decay and no ringing.
Cross-modal physical commonsense (AV-PC)
- Each thud onset aligns in time with a visible tap of the stick on the cushion.