WorldLines
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Embodied Planning | WorldLines 21 action-dense samples downstream planning probe | Plan Judge68.4 | 5 | |
| Embodied Task Planning | WorldLines Downstream Embodied (planning set) | Plan Judge Score68.4 | 5 | |
| Memory Question Answering | WorldLines Memory QA samples | Judge Score71.3 | 5 |
Showing 3 of 3 rows