A drumstick taps a metal railing with a clear ringing ping. Then taps a rubber mat with a dry dead thud.
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 drumstick
- a metal railing
- a rubber mat
Event: a drumstick taps a surface
Audio presence
- a drumstick
Sound: a drumstick tap
Key standards
Visual physical commonsense (V-PC)
- The drumstick makes visible contact with both a metal railing and a rubber mat at distinct points in the clip.
Audio physical commonsense (A-PC)
- The metal-railing tap is a clear ringing metallic ping with sustain, and the rubber-mat tap is a distinctly dry dead thud with rapid decay.
Cross-modal physical commonsense (AV-PC)
- Each tap sound coincides in time with a visible drumstick contact on its corresponding surface.
- The ringing metallic ping with sustain corresponds to the drumstick contacting the metal railing.
- The dry dead thud with rapid decay corresponds to the drumstick contacting the rubber mat.