Ceramic plates are stacked one by one with bright clinks. Then plastic plates are stacked the same way with dull quiet thuds.
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
- ceramic plates
- plastic plates
Event: plates are stacked one by one
Audio presence
- ceramic plates
- plastic plates
Sound: plates stacking
Key standards
Visual physical commonsense (V-PC)
- Both a ceramic stack and a plastic stack are visibly present at distinct points in the clip, with plates resting stably on the stack below them.
Audio physical commonsense (A-PC)
- The ceramic-stack sounds have a bright high-frequency clink timbre and the plastic-stack sounds have a distinctly duller, quieter thud timbre.
Cross-modal physical commonsense (AV-PC)
- Each stacking sound coincides in time with a visible plate-on-plate contact.
- The bright high-frequency clink corresponds to the ceramic stack.
- The duller, quieter thud corresponds to the plastic stack.