← all videos

A wine glass is tapped and rings at a high clear pitch. Water is poured in halfway, and the next tap rings noticeably lower.

C2-1-21 Event Transition · source_body principle: Mass Loading -> Pitch (Mechanics)
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 wine glass
  • water

Event: a wine glass is tapped

Audio presence

  • a wine glass

Sound: a wine glass tap ring

Key standards

Visual physical commonsense (V-PC)

  • The wine glass is visibly tapped once when empty and tapped again after water is poured at least partway in.

Audio physical commonsense (A-PC)

  • The second tap ring with water is noticeably lower in pitch than the first tap ring on the empty glass.
  • The tap sound has the characteristic high crystal ring of a wine glass.

Cross-modal physical commonsense (AV-PC)

  • Each tap sound aligns in time with a visible tap on the wine glass.
  • The lower-pitched tap corresponds to the water-filled wine glass.
  • The higher-pitched tap corresponds to the empty wine glass.