A frog visibly inflates its throat sac and vocalizes in close-up, but instead of a frog call it produces a clear sheep bleat that is perfectly synchronized with the motion and clearly originates from the frog.
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 frog
Event: a frog inflates its throat sac and vocalizes in close-up
Audio presence
- a frog
Sound: a sheep bleat
Key standards
Visual physical commonsense (V-PC)
- A clearly identifiable frog is visible in close-up and visibly inflates its throat sac and opens its mouth in continuous physically plausible vocalization motion.
- The animal in the frame retains its frog anatomy, skin, eyes, and body shape throughout the clip without morphing into a sheep or other species.
Audio physical commonsense (A-PC)
- The vocalization sound is a clear sheep bleat with the pitch, formant structure, and articulation of a real sheep call.
- The audio contains no frog croak or any amphibian vocalization at any point.
Cross-modal physical commonsense (AV-PC)
- Each bleat sound onset aligns in time with the frog's visible throat sac inflation and mouth motion, with the sound originating from the visible frog as the only on-screen animal.