A finger flicks a loose rubber band, producing a low buzzy twang. Stretched tighter and flicked again, the tone jumps noticeably higher.
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 rubber band
- a finger
Event: a finger flicks a rubber band
Audio presence
- a rubber band
Sound: a rubber band twang
Key standards
Visual physical commonsense (V-PC)
- The rubber band is flicked twice, and between the two flicks it is visibly stretched tighter.
- The flicked object is a thin elastic rubber band.
Audio physical commonsense (A-PC)
- The second twang is noticeably higher in pitch than the first twang.
- The twang sound is the elastic-pluck resonance of a real rubber band.
Cross-modal physical commonsense (AV-PC)
- Each twang sound aligns in time with a visible flick of the rubber band.
- The higher-pitched twang corresponds to the visibly tighter rubber band state.
- The lower-pitched twang corresponds to the visibly looser rubber band state.