From a fixed camera, a race car drives past in a straight line at constant high speed. The engine note rises as it approaches and falls as it speeds away.
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 race car
- a road
Event: a race car drives past a fixed camera
Audio presence
- a race car engine
Sound: an engine note
Key standards
Visual physical commonsense (V-PC)
- The race car approaches, passes, and recedes from the fixed camera at roughly constant speed.
Audio physical commonsense (A-PC)
- The engine note pitch is noticeably higher during the approach segment than during the receding segment.
Cross-modal physical commonsense (AV-PC)
- The transition from higher to lower engine pitch aligns in time with the race car's visible passage past the camera.