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

NIV

Benchmarks

Task NameDataset NameSOTA ResultTrend
Procedure PlanningNIV T=3 (test)
SR56.51
30
Procedure PlanningNIV
Success Rate (SR)34.44
26
Procedure PlanningNIV T=4 (test)
SR43.81
19
Procedure PlanningNIV T=4
SR20.14
4
Procedure PlanningNIV T=3
Success Rate24.68
4
Procedure PlanningNIV T=6 (test)
SR17.53
2
Procedure PlanningNIV T=5 (test)
SR21.58
2
Showing 7 of 7 rows