Keys fall onto a tile floor with a sharp metallic jangling. Then fall onto thick carpet with only a soft muffled thud.
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
- keys
- a tile floor
- thick carpet
Event: keys fall onto a tile floor and onto carpet
Audio presence
- keys
- a tile floor
- carpet
Sound: keys landing
Key standards
Visual physical commonsense (V-PC)
- A bundle of keys falls under gravity onto a hard tile floor first, then keys fall onto thick carpet.
- The falling objects remain a coherent set of keys throughout the clip.
Audio physical commonsense (A-PC)
- The tile landing produces a sharp bright metallic jangle.
- The carpet landing produces a soft muffled thud noticeably quieter and duller than the tile landing.
- Each landing sound is the natural impact of keys striking its surface.
Cross-modal physical commonsense (AV-PC)
- Each landing-sound onset aligns in time with a visible key impact on its corresponding surface.