An ice cube drops into a glass cup with a sharp clink. Then drops into a stainless steel tumbler with a brighter ringing ping.
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
- an ice cube
- a glass cup
- a stainless steel tumbler
Event: an ice cube drops into a container
Audio presence
- an ice cube
- a glass cup
- a stainless steel tumbler
Sound: ice cube impact in container
Key standards
Visual physical commonsense (V-PC)
- Ice cubes visibly land inside both a glass cup and a stainless steel tumbler at distinct points in the clip.
Audio physical commonsense (A-PC)
- The ice-in-glass impact has a sharp glass-clink timbre and the ice-in-steel impact has a distinctly brighter ringing metallic ping.
Cross-modal physical commonsense (AV-PC)
- Each impact sound coincides in time with a visible landing of the ice cube inside its container.
- The sharp glass-clink corresponds to the ice landing in the glass cup.
- The brighter ringing metallic ping corresponds to the ice landing in the stainless steel tumbler.