A person drops a metal tool in a large parking garage. The clang is followed by a long ringing tail bouncing between the concrete walls.
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 metal tool
- a parking garage
Event: a metal tool is dropped onto a garage floor
Audio presence
- a metal tool
Sound: a metallic clang
Key standards
Visual physical commonsense (V-PC)
- A person drops or throws a metal tool that lands on the floor of a parking garage.
- The tool maintains a rigid metallic shape throughout the drop and impact.
Audio physical commonsense (A-PC)
- The metallic clang is followed by a long ringing reverberation tail.
- The reverberation is consistent with reflections between concrete parking-garage walls.
Cross-modal physical commonsense (AV-PC)
- The clang onset in the audio aligns in time with the visible impact of the tool on the floor.
- The ringing reverberation in the audio follows the visible impact event as its consequence.