| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-Horizon (2-Obj) | Household Simulation | Success Rate4 | 2 | |
| Spatial Relation | Household Simulation | Success Rate7 | 2 | |
| Linguistic Variation | Household Simulation | Success Rate0.7 | 2 | |
| Explicit Placement | Household Simulation | Success Rate6 | 2 |