| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Streaming Spatial Reasoning | S3-Eval Sim | Overall Accuracy80.5 | 20 | |
| Embodied Spatial Reasoning | S3-Eval (real part) | Overall Score82.1 | 20 | |
| Active Spatial Understanding | S3-Eval (simulation) | Overall Score62.9 | 4 | |
| Active Vision Spatial Understanding | S3-Eval real | Overall Score57.8 | 4 |