Music plays from a smartphone resting on a desk in a quiet room; the phone is then placed inside a closed wooden drawer, yet after the drawer shuts, the music sounds louder and clearer than it did in the open.
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 smartphone
- a desk
- a wooden drawer
Event: a smartphone playing music is placed inside a wooden drawer and the drawer closes
Audio presence
- a smartphone
Sound: music from a smartphone
Key standards
Visual physical commonsense (V-PC)
- A smartphone visibly plays music while resting on a desk in a quiet room at the start of the clip.
- The smartphone is then placed inside a wooden drawer and the drawer is visibly closed, with the phone fully enclosed inside the closed drawer for the rest of the clip.
Audio physical commonsense (A-PC)
- The music plays continuously throughout the clip with consistent musical content.
- The music sounds louder and clearer once the drawer is closed than it did when the phone was on the open desk.
Cross-modal physical commonsense (AV-PC)
- The shift to louder and clearer music aligns in time with the moment the wooden drawer visibly closes around the smartphone.