Two identical tuning forks sit on wooden boxes a foot apart. A hand strikes one with a mallet, and after a moment the other one starts ringing on its own.
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
- two tuning forks
- wooden boxes
- a mallet
- a hand
Event: a hand strikes one of two tuning forks with a mallet
Audio presence
- two tuning forks
Sound: a tuning fork ring
Key standards
Visual physical commonsense (V-PC)
- Two canonical U-tine tuning forks sit on wooden boxes a small distance apart.
- A mallet visibly strikes one of the two tuning forks during the clip.
Audio physical commonsense (A-PC)
- The struck fork rings at a clear fundamental pitch.
- A second ringing tone at the same fundamental pitch emerges after a short delay, originating from the unstruck fork.
Cross-modal physical commonsense (AV-PC)
- The first ring onset in the audio aligns in time with the visible mallet strike.
- The second ringing tone in the audio is paired with visible vibration of the second fork without any visible contact on it.