IFEval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
IFEval
95IFEval Accuracy
854
IFEval
90.39Accuracy (IFEval)
101
IFEval
94.64IFEval Score
92
IFEval (test)
84.8IFEval Score
92
IFEval
87.5Genuine-Followup Rate
65
IFEval
98.9Accuracy (Greedy)
52
IFEval
88.92Avg. Score (IFEval)
49
IFEval
81.2Win Rate
36
IFEval
80.2IFEval
34
IFEval Inverse
83.7Inv-IF
34
IFEval
86.69IFEval Score
32
IFEval
76.26IF-RT Score
30
IFEval v1 (test)
79.85Accuracy
28
IFEval
64.23Avg@k
27
IFEval strict prompt
90.2pass@1
26
IFEval
86.5IFEval Score
25
IFEval
81Strict Accuracy
24
PPE-IFEval
76Score
24
IFEval
74.49Accuracy
23
IFEval In-Domain
0.871Precision (L)
23
IFEval
85.4Score (%)
22
IFEval
47.67Average Score
21
IFEval
90Strict Accuracy
21
IFEval
74Improvement Score
21
IFEval
84.63IFScore
21