A mallet strikes a xylophone from the longest bar to the shortest. Each bar rings higher than the one before, from deep warm tones to bright high notes.
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 mallet
- a xylophone
Event: a mallet strikes xylophone bars
Audio presence
- a xylophone
Sound: a bright, pitched xylophone bar strike
Key standards
Visual physical commonsense (V-PC)
- The mallet strikes the xylophone bars in sequence from the longest bar to the shortest, with each strike landing on a progressively shorter bar.
- The xylophone has recognizable graduated wooden bars of clearly decreasing length, arranged in order.
Audio physical commonsense (A-PC)
- Each successive ring has a higher pitch than the previous one, rising monotonically across the sequence.
- The strike sound has the characteristic bright wooden timbre of a xylophone bar, not a dull wooden knock or a metallic ring.
Cross-modal physical commonsense (AV-PC)
- Each ring onset aligns in time with a visible mallet strike on a bar.
- Each successively higher pitch in the audio corresponds to a visibly shorter bar being struck.