A ticking clock is clearly audible in a quiet room. A vacuum cleaner turns on nearby and the ticking disappears under the motor noise.
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 clock
- a vacuum cleaner
- a room
Event: a vacuum cleaner turns on near a ticking clock in a room
Audio presence
- a clock
- a vacuum cleaner
Sound: ['clock ticking', 'vacuum cleaner motor noise']
Key standards
Visual physical commonsense (V-PC)
- A clock with a visible face and a vacuum cleaner are both shown, and the vacuum is turned on by a person during the clip while the clock remains visible throughout.
Audio physical commonsense (A-PC)
- Clock ticking is clearly audible before the vacuum starts, and the ticking becomes inaudible once the vacuum motor noise is active.
Cross-modal physical commonsense (AV-PC)
- The disappearance of the ticking aligns in time with the visible moment the vacuum cleaner turns on.