Two hollow pipes with the same diameter but clearly different lengths are struck one after the other in the same setup; despite the longer pipe being visibly larger, it sounds higher in pitch than the shorter pipe.
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
- two hollow pipes
Event: two hollow pipes of different lengths are struck one after the other
Audio presence
- two hollow pipes
Sound: pipe tones
Key standards
Visual physical commonsense (V-PC)
- Two hollow pipes with the same diameter but clearly different lengths are visible, and each is visibly struck one after the other with continuous physically plausible motion.
- Both pipes remain hollow rigid pipes throughout the clip, with the size difference between them clearly visible.
Audio physical commonsense (A-PC)
- Each strike produces a sustained metallic tone with the bright resonant timbre of a real struck hollow pipe.
- The tone from the longer pipe is noticeably higher in pitch than the tone from the shorter pipe.
Cross-modal physical commonsense (AV-PC)
- Each tone onset aligns in time with a visible strike of the corresponding pipe.
- The higher-pitched tone corresponds to the visibly longer pipe, and the lower-pitched tone corresponds to the visibly shorter pipe.