Planning on TravelPlanner (TP-test)
91.76Avg Pass RateSyn-PlanningBench
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Syn-PlanningBenchTraining Data=Syn-PlanningBench2026.05 | 91.76 | 47.93 | |
| Human-AuthoredTraining Data=Human-Authored2026.05 | 88.56 | 34.91 | |
| BaseTraining Data=Base2026.05 | 84.11 | 35.72 |