| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TravelPlanner (test) | Qwen3-14B | Final Pass Rate87.4 | 49 | 18d ago | |
| TravelPlanner | ToRL | Average Tokens Used14.8 | 46 | 2mo ago | |
| TravelPlanner (val) | MIRROR | Delivery Rate100 | 42 | 1mo ago | |
| Travel Planning | PIVOT | Composite Score96.2 | 30 | 2mo ago | |
| TravelPlanner 1000 tasks (test) | HiMAP-Travel | Commonsense Score (Micro)94.72 | 13 | 4mo ago | |
| MemoryArena Group Travel Planning 1.0 (test) | MAGE | Success Rate (SR)15.19 | 8 | 1mo ago | |
| ChinaTravel Medium | Behavior Forest | Final Pass Rate77.82 | 8 | 2mo ago | |
| ChinaTravel (Human) | Behavior Forest | Delivery Rate96.73 | 5 | 3mo ago | |
| ChinaTravel Easy | Behavior Forest | Delivery Rate98.89 | 5 | 3mo ago | |
| TravelGym | MCPE | Productivity1.533 | 2 | 1mo ago |