A person presses a stethoscope against a wall and hears the muffled sound of a television playing in the next room.
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 person
- a stethoscope
- a wall
Event: a person presses a stethoscope against a wall
Audio presence
- a television
Sound: muffled television playback
Key standards
Visual physical commonsense (V-PC)
- A stethoscope's chest-piece is visibly pressed against the wall while the earpieces remain connected to the person's ears.
- The television is in a separate room beyond the wall, not visibly present in the listener's room.
Audio physical commonsense (A-PC)
- A muffled television playback with crowd, dialogue, or music character is audible during the stethoscope-wall contact.
Cross-modal physical commonsense (AV-PC)
- The audible television sound onsets at the moment the stethoscope makes contact with the wall.