A person places their ear on a railroad track and hears the distant rumble of a train approaching long before the sound arrives through the air.
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 railroad track
Event: a person presses their ear to a railroad track
Audio presence
- an approaching train
Sound: distant train rumble through steel
Key standards
Visual physical commonsense (V-PC)
- A person lies down and places their ear directly onto the rail with continuous motion.
Audio physical commonsense (A-PC)
- A low-frequency rumble consistent with sound conducted through solid steel is audible while the ear is in contact with the track.
Cross-modal physical commonsense (AV-PC)
- The track-borne rumble onsets when the ear contacts the rail and substantially diminishes when the ear lifts off.