A large gong is struck and rings deep and loud. Then an assistant presses both palms flat against the surface and the ringing dies immediately.
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 large gong
- an assistant's palms
Event: an assistant presses both palms on a struck gong
Audio presence
- a large gong
Sound: gong ring
Key standards
Visual physical commonsense (V-PC)
- A large gong is visibly struck with a mallet during the clip.
- An assistant's both palms visibly press flat against the gong surface while it is still ringing.
Audio physical commonsense (A-PC)
- A deep loud ringing tone from the gong is audible after the mallet strike.
- The ring dies almost instantly once both palms contact the gong, with no residual ring.
Cross-modal physical commonsense (AV-PC)
- The ring onset in the audio aligns in time with the visible mallet strike.
- The abrupt end of the ring coincides in time with the visible moment both palms contact the gong surface.