TRIP-Bench
Benchmarks
TaskDatasetSOTA resultTrendResults
TRIP-Bench (Hard LIT)
4,400Loose Success
32
TRIP-Bench Overall
45Loose Success Score
16
TRIP-Bench Hard PMR
36Loose Success
16
TRIP-Bench (Hard FIT)
18Loose Success Rate
16
TRIP-Bench Mid
55Loose Success Rate
16
TRIP-Bench Easy
71Loose Success Count
16