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

Hallucination Detection on RAGTruth

0.8535AUROC

SpikeScore

0.371460.4966050.621750.746895Jan 27, 2026Feb 14, 2026Mar 4, 2026Mar 22, 2026Apr 9, 2026Apr 27, 2026May 16, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.01
0.8535
2026.01
0.8291
2026.01
0.8154
2026.05
0.78
2026.01
0.7653
2026.01
0.7631
2026.01
0.7426
2026.01
0.7416
2026.01
0.7405
2026.01
0.6974
2026.01
0.6958
2026.01
0.6904
2026.01
0.6796
2026.01
0.6479
2026.01
0.644
2026.01
0.642
2026.01
0.6388
2026.01
0.6338
2026.01
0.6329
2026.01
0.6292
2026.01
0.6284
2026.01
0.621
2026.01
0.6191
2026.01
0.6179
2026.01
0.6151
2026.01
0.6044
2026.01
0.6037
2026.01
0.6011
2026.01
0.5936
2026.01
0.5904
2026.01
0.5874
2026.01
0.5839
2026.05
0.57
2026.05
0.57
2026.01
0.5587
2026.01
0.5547
2026.05
0.55
2026.05
0.55
2026.05
0.54
2026.01
0.5253
2026.01
0.5239
2026.05
0.52
2026.05
0.52
2026.05
0.52
2026.05
0.52
2026.05
0.51
2026.05
0.51
2026.05
0.5
2026.05
0.5
2026.05
0.5
2026.05
0.5
2026.01
0.4988
2026.05
0.49
2026.05
0.47
2026.05
0.47
2026.05
0.46
2026.05
0.46
2026.05
0.39