A person blows across the opening of a long pipe, producing a deep low tone, then blows across a much shorter pipe, producing a bright, noticeably higher tone.
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 long pipe
- a short pipe
- a person
Event: a person blows across the opening of a pipe
Audio presence
- a pipe
Sound: a blown pipe tone
Key standards
Visual physical commonsense (V-PC)
- Two pipes of clearly different lengths are visible, and the person blows the long pipe first and the short pipe second, in that order.
Audio physical commonsense (A-PC)
- The tone from the short pipe is noticeably higher in pitch than the tone from the long pipe.
Cross-modal physical commonsense (AV-PC)
- Each blown tone aligns in time with a visible blow across the corresponding pipe opening.
- The higher-pitched tone corresponds to the visibly shorter pipe; the lower-pitched tone corresponds to the visibly longer pipe.