| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TravelPlanner | AgentVerse | Delivery Rate100 | 13 | 4d ago | |
| Maze2D U-Maze | RDM | Normalized Return185.3 | 10 | 4d ago | |
| Maze2D Medium | RDM | Normalized Return159.3 | 5 | 4d ago | |
| GeoPlan-Bench | Earth-Agent-MAS | Recall66 | 4 | 4d ago | |
| Multi2D Large | RDM | Normalized Return195.4 | 3 | 4d ago | |
| Multi2D Medium | RDM | Normalized Return155.1 | 3 | 4d ago | |
| Multi2D U-Maze | RDM | Normalized Return152.1 | 3 | 4d ago |