A referee blows a whistle on a sports field. Players nearby hear a piercing blast. The scene cuts to the far seats, where spectators hear only a thin distant tweet.
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 referee
- a whistle
- players
- a sports field
- spectator seats
Event: a referee blows a whistle on a sports field
Audio presence
- a whistle
Sound: a whistle blast
Key standards
Visual physical commonsense (V-PC)
- A near-scene shows the referee blowing the whistle on the field, and a far-scene shows the spectator-seat vantage of the same field.
Audio physical commonsense (A-PC)
- The whistle blast is clearly audible as a piercing tone in the near-scene and remains audible as a thinner and quieter whistle tweet in the far-scene.
Cross-modal physical commonsense (AV-PC)
- The whistle's loudness in each scene matches the visible camera distance from the referee.