A metal bowl rings brightly when struck empty. After filling it partway with sand, it rings noticeably lower.
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 metal bowl
- sand
Event: a metal bowl is struck
Audio presence
- a metal bowl
Sound: a metal bowl ring
Key standards
Visual physical commonsense (V-PC)
- The metal bowl is visibly struck once when empty and struck again after sand is poured partway in, with each strike contacting the bowl's wall or body rather than the sand pile inside.
Audio physical commonsense (A-PC)
- The second ring with sand added is noticeably lower and more damped than the first ring on the empty bowl.
- The strike sound has the characteristic bright metallic ring of a struck metal bowl.
Cross-modal physical commonsense (AV-PC)
- Each ring onset aligns in time with a visible strike of the bowl.
- The lower and more damped ring corresponds to the bowl with sand.
- The brighter ring corresponds to the empty bowl.