A wooden stick presses and taps a sponge. The sound is extremely soft and muted, almost disappearing immediately after contact.
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 sponge
Event: a stick presses and taps a sponge
Audio presence
- a wooden stick
- a sponge
Sound: stick-on-sponge contact
Key standards
Visual physical commonsense (V-PC)
- The sponge compresses under the stick and visibly recovers to its original shape when the stick is lifted.
Audio physical commonsense (A-PC)
- The contact sound is extremely soft and muted with near-immediate decay.
Cross-modal physical commonsense (AV-PC)
- Each faint contact sound aligns in time with a visible press or tap of the stick on the sponge.