LUN
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
LUN
69.82Macro F1
17
LUN (test)
71.28Micro F1
9
LUN (test)
64.94Accuracy
7
LUN >2048 tokens (test)
79.59Accuracy
4
LUN neutralized (test)
70.67Accuracy
2
LUN original (test)
75.13Accuracy
2
LUN (>1024 tokens) (test)
59.11Accuracy
2
LUN all (test)
67.41Accuracy
2