A tuning fork is struck and rings at a clear pitch. Then a small clip is attached to one prong, and the next strike rings noticeably lower.
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 tuning fork
- a clip
Event: a tuning fork is struck
Audio presence
- a tuning fork
Sound: a tuning fork ring
Key standards
Visual physical commonsense (V-PC)
- The tuning fork is visibly struck twice, and a small clip is visibly attached to one prong between the first and second strikes.
- The instrument is a tuning fork with two parallel prongs joined at a U-shaped handle.
Audio physical commonsense (A-PC)
- The second ring with the clip attached is noticeably lower in pitch than the first ring without the clip.
- The strike sound has the sustained bright metallic ring of a tuning fork.
Cross-modal physical commonsense (AV-PC)
- Each ring onset aligns in time with a visible strike of the tuning fork.
- The lower-pitched ring corresponds to the state with the clip attached.
- The higher-pitched ring corresponds to the state without the clip.