Model Ranking
Overall is selected by default. World-model-feature scores range from 1 to 5; higher is better.
| Rank | Model | Score |
|---|
Latest PlayWorld Results
VQA evaluation across four dimensions in PlayWorld. Scores range from 1 to 5; higher is better.
| Model | Geometry Consistency ↑ | Interaction Fidelity ↑ | Insight Evolution ↑ | Out-of-sight Evolution ↑ | Overall ↑ |
|---|