← all videos

A dog stands on the left side of a room and lets out a deep bark. Then a cat on the right side answers with a sharp meow.

C1-2-08 Steady State · source_anchoring principle: Multi-Source Spatial Separation (Wave)
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 dog
  • a cat
  • a room

Event: a dog barks and a cat meows in a room

Audio presence

  • a dog
  • a cat

Sound: ['dog bark', 'cat meow']

Key standards

Visual physical commonsense (V-PC)

  • A visible dog stays at a stable position on the left side of the room and visibly barks during the bark event.
  • A visible cat stays at a stable position on the right side of the room and visibly meows during the meow event.

Audio physical commonsense (A-PC)

  • The dog bark carries the deep low-frequency timbre of a real canine bark.
  • The cat meow carries the sharp high-frequency timbre of a real feline meow.

Cross-modal physical commonsense (AV-PC)

  • The dog bark is localized to the left side of the audio field, matching the dog's visible left-side position.
  • The cat meow is localized to the right side of the audio field, matching the cat's visible right-side position.