A drummer loosens the lugs on a drum head and hits it for a low flabby thud. After tightening the lugs, the next hit rings brighter and sharper.
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 drum
- a drummer
Event: a drum head is struck
Audio presence
- a drum
Sound: a drum hit
Key standards
Visual physical commonsense (V-PC)
- The drum head is struck twice, and between the two strikes the drum's lugs are visibly turned by hand or with a tool.
Audio physical commonsense (A-PC)
- The second drum hit is noticeably brighter and higher in pitch than the first drum hit.
Cross-modal physical commonsense (AV-PC)
- Each drum hit sound aligns in time with a visible strike on the drum head.
- The brighter and higher-pitched hit follows the lug-tightening adjustment.
- The lower and flabbier hit follows the lug-loosening adjustment.