TravelPlanner
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
TravelPlanner (test)
87.4Final Pass Rate
49
TravelPlanner
14.8Average Tokens Used
46
TravelPlanner (val)
100Delivery Rate
42
TravelPlanner #180 (val)
95.64CS-Micro
22
TravelPlanner
100Delivery Rate
13
TravelPlanner 1000 tasks (test)
94.72Commonsense Score (Micro)
13
TravelPlanner
59.25Pass@1
12
TravelPlanner
0.225Success Rate (CS/HD Avg)
12
TravelPlanner
100Delivery Rate
11
TravelPlanner (val)
3.33Final Pass Rate
8
TravelPlanner (val)
7.22Final Pass Rate
8
TravelPlanner Hard
100Delivery Rate
5
TravelPlanner Medium
100Delivery Rate
5
TravelPlanner Easy
100Delivery Rate
5
TravelPlanner
0.833Commonsense Score (CS)
4
TravelPlanner (test)
0.271Success Rate
4
TravelPlanner
17.5Effect Improvement
3
TravelPlanner Avg.
91.93Avg-pass Rate
3
TravelPlanner (TP-test)
91.76Avg Pass Rate
3
TravelPlanner (val)
91.04Avg-pass
3
TravelPlanner (train)
93Avg-pass Rate
3