A wine glass is tapped and rings clearly. Then a finger gently touches the rim and the ringing stops instantly.
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
- a finger
Event: a finger touches the rim of a tapped wine glass
Audio presence
- a wine glass
Sound: wine glass ring
Key standards
Visual physical commonsense (V-PC)
- A stemmed wine glass is tapped once and rings clearly during the clip.
- A finger visibly touches the rim of the ringing wine glass.
Audio physical commonsense (A-PC)
- A clear ringing tone from the wine glass is audible after the tap.
- The ringing tone decays to silence almost instantly once the finger contacts the rim, with no residual ring.
Cross-modal physical commonsense (AV-PC)
- The tap transient in the audio aligns in time with the visible tap on the wine glass.
- The abrupt end of the ring coincides in time with the visible moment the finger contacts the rim.