A ceramic mug is set down on a granite countertop, producing a hard bright clink with a brief ring.
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 ceramic mug
- a granite countertop
Event: a mug is set down on a countertop
Audio presence
- a ceramic mug
- a granite countertop
Sound: mug-on-countertop clink
Key standards
Visual physical commonsense (V-PC)
- The mug is lowered by a hand and visibly contacts the countertop, with all parts of the mug remaining intact through and after contact.
Audio physical commonsense (A-PC)
- The clink has a hard bright brittle ceramic-on-stone timbre with a brief ringing tail.
Cross-modal physical commonsense (AV-PC)
- The clink onset aligns in time with the visible moment the mug contacts the countertop.