A drummer rolls on a snare drum, starting with barely audible taps and building gradually to thunderous hits.
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 drummer
- a snare drum
- drumsticks
Event: a drummer performs a roll on a snare drum
Audio presence
- a snare drum
Sound: a snare drum roll
Key standards
Visual physical commonsense (V-PC)
- The drummer performs a continuous roll specifically on the snare drum, with the stick motion visibly intensifying from light taps to larger motions throughout the clip.
Audio physical commonsense (A-PC)
- The roll rises progressively in loudness from barely-audible taps to thunderous hits, in a smooth continuous crescendo.
- The sound is a real snare drum roll.
Cross-modal physical commonsense (AV-PC)
- The rising loudness aligns in time with the visibly intensifying stick motion.
- The loudest hits correspond to the largest visible stick amplitudes.
- The quietest taps correspond to the smallest visible stick motion.