| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-horizon reasoning | EXPLORE-Bench Full | Sobj Score65.59 | 6 | |
| Long-horizon reasoning | EXPLORE-Bench Long | Sobj Score59.37 | 6 | |
| Long-horizon reasoning | EXPLORE-Bench Medium | Sobj Score66.71 | 6 | |
| Long-horizon reasoning | EXPLORE-Bench Short | Object Score66.12 | 6 |