A customer stands still in a supermarket aisle as a store cart carrying a visible loudspeaker rolls from directly in front, past the listener's right side, and then behind them while playing music; instead of shifting from front to side to back, the sound remains fixed in the center the entire time.
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 customer
- a store cart
- a loudspeaker
- a supermarket aisle
Event: a store cart with a loudspeaker rolls past a stationary listener from front to right side to behind
Audio presence
- a loudspeaker
Sound: music from a loudspeaker
Key standards
Visual physical commonsense (V-PC)
- A customer stands still in a supermarket aisle while a store cart carrying a visible loudspeaker rolls past during the clip.
- The cart visibly travels from directly in front of the listener, past the listener's right side, and then behind them.
Audio physical commonsense (A-PC)
- Continuous music plays uninterrupted throughout the clip from the loudspeaker on the cart.
Cross-modal physical commonsense (AV-PC)
- The music remains localized in the center of the audio field throughout the clip while the cart visibly rolls from front to side to behind the listener.