A metal ruler sticks out over the edge of a desk. A finger flicks the tip and it buzzes at a high pitch. Slid out further and flicked again, the buzz is much 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 metal ruler
- a desk
Event: a finger flicks the free end of a metal ruler overhanging a desk edge
Audio presence
- a metal ruler
Sound: a metallic buzz from a flicked ruler
Key standards
Visual physical commonsense (V-PC)
- The ruler is flicked twice, and between the two flicks the length of the ruler overhanging the desk visibly increases.
- The ruler remains rigid and straight throughout the clip, with visible gradations typical of a metal ruler.
Audio physical commonsense (A-PC)
- The second buzz has a noticeably lower pitch than the first buzz.
Cross-modal physical commonsense (AV-PC)
- Each buzz onset aligns in time with a visible flick of the ruler.
- The lower-pitched buzz corresponds to the flick with the longer overhang; the higher-pitched buzz corresponds to the flick with the shorter overhang.