A person claps in a large empty hall with a hard concrete floor and bare parallel walls. The clap rebounds into a fluttering string of fast repeating echoes that buzzes between the walls for several seconds.
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 person
- a large empty hall
- a concrete floor
- parallel walls
Event: a person claps inside a large empty hall
Audio presence
- a person
Sound: a hand clap
Key standards
Visual physical commonsense (V-PC)
- A single person performs a single hand clap inside a large hall.
- The hall has bare hard parallel walls and a hard floor.
Audio physical commonsense (A-PC)
- A rapid-repeating flutter pattern of fast clap reflections is audible after the clap.
- The flutter pattern persists for several seconds before fading.
Cross-modal physical commonsense (AV-PC)
- The initial clap transient in the audio aligns in time with the visible hand-clap action.
- The flutter-echo string follows the single visible clap as its consequence.