A fire truck siren wails next to a person on the curb, painfully loud. The scene cuts to several blocks away, where the same siren is a faint distant wail.
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 fire truck
- a person
- a curb
- a street
Event: a fire truck with a wailing siren is near a person on a curb
Audio presence
- a fire truck siren
Sound: a siren wail
Key standards
Visual physical commonsense (V-PC)
- A close-up scene shows a fire truck next to a person on a curb, and a separate distant scene shows the same fire truck visibly several blocks away.
Audio physical commonsense (A-PC)
- The siren is dramatically loud in the close-up scene and noticeably quieter in the distant scene.
Cross-modal physical commonsense (AV-PC)
- The siren's loudness in each scene matches the visible proximity of the fire truck.