IFBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
IFBench
77.8Accuracy
72
IFBench
82.9Pass@1 (Strict)
72
IFBench
82IFBench Score
68
IFBench
76.5Accuracy
41
IFBench (test)
55.95Score
36
IFBench
84.1Accuracy
30
IFBench
73.2Score
23
IFBench
79.79IFBench Score
23
IFBench
34.69Prompt-level Accuracy
21
IFBench
75.4IFBench Score
19
IFBench
36Accuracy
18
IFBench
69.3Accuracy
17
IFBench Hard
78Accuracy
16
IFBench Normal
80.5Accuracy
16
IFBench Simple
87.2Accuracy
16
IFBench-I
73.96Accuracy
15
IFBench prompt
73.4Accuracy
11
IFBench-P
17.4Accuracy
10
IFBench
23.88IFBench Score
9
IFBench
57.3Pr. (S)
8
IFBench
2,688LLM Throughput (tokens/s)
8
IFBench prompt
77.8Score
7
IFBench
65Exact Match (EM)
7
IFBench
41.7pass@1
7
IFBench (test)
57.9Accuracy
7