Boiling water is poured into a ceramic mug. As the mug fills, the pouring sound rises in pitch.
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
- boiling water
- a ceramic mug
Event: water is poured into a ceramic mug
Audio presence
- a ceramic mug
Sound: water pouring into a mug
Key standards
Visual physical commonsense (V-PC)
- Water is poured from a kettle into a ceramic mug, and the water level visibly rises continuously toward the rim.
Audio physical commonsense (A-PC)
- The pouring sound rises in pitch as the mug fills.
- The pitch interpolates smoothly across the duration of the pour.
- The audible track is a real water-pour sound from the visible pour.
Cross-modal physical commonsense (AV-PC)
- The rising pitch in the audio aligns temporally with the visibly rising water level in the mug.