| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Agent Task | Agent | Accuracy100 | 16 | |
| Goal-Oriented Navigation | AGENT new concepts from new initial states (test) | Accuracy73 | 9 | |
| Agentic Tasks | Agent | MTP Acceptance Rate99.1 | 5 | |
| Agent interaction | Agent | Clean Success (Eager)100 | 4 |