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

IF

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-class ClassificationIF (test)
Accuracy80.27
32
Instruction FollowingIF
IF Score39.2
8
Instruction FollowingIF XLow Tier
R Rate64.4
3
Instruction FollowingIF Low Tier
R Score61.2
3
Instruction FollowingIF High Tier
Response Rate74.5
3
Showing 5 of 5 rows