Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Hallucination Detection on Average Cross-domain

0.7874Mean AUROC

SpikeScore

0.4864240.5645620.64270.720838Jan 27, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
0.7874
2026.01
0.786
2026.01
0.7474
2026.01
0.7473
2026.01
0.7463
2026.01
0.7439
2026.01
0.7435
2026.01
0.7381
2026.01
0.7072
2026.01
0.7032
2026.01
0.7029
2026.01
0.702
2026.01
0.6963
2026.01
0.6953
2026.01
0.694
2026.01
0.6917
2026.01
0.683
2026.01
0.67
2026.01
0.6699
2026.01
0.6644
2026.01
0.6636
2026.01
0.6622
2026.01
0.6503
2026.01
0.646
2026.01
0.6438
2026.01
0.6425
2026.01
0.6357
2026.01
0.6309
2026.01
0.6302
2026.01
0.6214
2026.01
0.6111
2026.01
0.5953
2026.01
0.5787
2026.01
0.5764
2026.01
0.5705
2026.01
0.5693
2026.01
0.5635
2026.01
0.5635
2026.01
0.5632
2026.01
0.5591
2026.01
0.5469
2026.01
0.5282
2026.01
0.5276
2026.01
0.5274
2026.01
0.527
2026.01
0.5212
2026.01
0.5186
2026.01
0.498