An ambulance with its siren blaring approaches a person on a sidewalk. As it gets closer the siren pitch rises higher, and as it speeds away the pitch drops lower.
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
- an ambulance
- a person
- a sidewalk
- a road
Event: an ambulance passes a person on a sidewalk
Audio presence
- an ambulance siren
Sound: a siren
Key standards
Visual physical commonsense (V-PC)
- The ambulance approaches, passes, and recedes from the observer along the road with continuous motion.
Audio physical commonsense (A-PC)
- The siren pitch is noticeably higher during the approach segment than during the receding segment.
Cross-modal physical commonsense (AV-PC)
- The transition from higher to lower siren pitch aligns in time with the ambulance's visible passage past the observer.