Children
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Children
48.25Accuracy
19
Children
71.53AUPRC
18
Children
93.85AUROC
18
Children
0.704Anomaly F1
18
Children (test)
29.4Accuracy
15
Children
27.9Macro-F1
14
Children LLM-embedded (test)
0.362Accuracy
10