A stone is thrown into a pond and hits the water with a clear splash. The splash sound happens at the exact moment the stone touches the surface.
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 stone
- a pond
Event: a stone enters a pond
Audio presence
- a pond
Sound: a water splash
Key standards
Visual physical commonsense (V-PC)
- A stone moves through the air under gravity-driven acceleration and enters the pond.
- The stone enters the water producing realistic ripples and a splash, and then sinks below the surface.
Audio physical commonsense (A-PC)
- The splash sound has a sharp water-impact onset followed by a brief watery scatter of droplets.
Cross-modal physical commonsense (AV-PC)
- The splash sound onset coincides with the visible moment the stone contacts the water surface.