Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TravelPlanner

Benchmarks

Task NameDataset NameSOTA ResultTrend
Travel PlanningTravelPlanner (test)
Final Pass Rate87.4
49
Travel PlanningTravelPlanner
Average Tokens Used14.8
46
Travel planningTravelPlanner (val)
Delivery Rate100
42
PlanningTravelPlanner #180 (val)
CS-Micro95.64
22
Long-horizon planningTravelPlanner
Delivery Rate100
13
Travel PlanningTravelPlanner 1000 tasks (test)
Commonsense Score (Micro)94.72
13
PlanningTravelPlanner
Pass@159.25
12
End-to-end planningTravelPlanner
Success Rate (CS/HD Avg)0.225
12
Constraint Satisfaction Plan GenerationTravelPlanner
Delivery Rate100
11
Multi-agent PlanningTravelPlanner (val)
Final Pass Rate3.33
8
Sole PlanningTravelPlanner (val)
Final Pass Rate7.22
8
PlanningTravelPlanner Hard
Delivery Rate100
5
PlanningTravelPlanner Medium
Delivery Rate100
5
PlanningTravelPlanner Easy
Delivery Rate100
5
Travel planning agentTravelPlanner
Commonsense Score (CS)0.833
4
PlanningTravelPlanner (test)
Success Rate0.271
4
PlanningTravelPlanner
Effect Improvement17.5
3
PlanningTravelPlanner Avg.
Avg-pass Rate91.93
3
PlanningTravelPlanner (TP-test)
Avg Pass Rate91.76
3
PlanningTravelPlanner (val)
Avg-pass91.04
3
PlanningTravelPlanner (train)
Avg-pass Rate93
3
Showing 21 of 21 rows