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

Trips

Benchmarks

Task NameDataset NameSOTA ResultTrend
Step-level correctness assessmentTrips (test)
PR-AUC79.9
22
Step-level reasoning verificationTrips
PR-AUC82.5
19
PlanningTrips (test)
Accuracy15.6
6
Showing 3 of 3 rows