| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-horizon procedural planning | EgoPlan-Bench All | Success Rate58.72 | 13 | |
| Long-horizon procedural planning | EgoPlan-Bench Out-of-Domain | Success Rate54.37 | 9 | |
| Long-horizon procedural planning | EgoPlan-Bench In-Domain | Success Rate62.46 | 9 | |
| Egocentric Action Planning | EgoPlan-bench v2 (test) | Daily life Success Rate64.01 | 7 |