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

Multi-IF

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction FollowingMulti-IF
Score85.56
41
Multi-turn instruction-followingMulti-IF
Turn 1 Score95.02
18
Instruction FollowingMulti-IF PT
Accuracy88
15
Long-context & Multi-turn DialogueMulti-IF turn-3
Score74.8
4
Showing 4 of 4 rows