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

Hallucination Detection on Belebele

0.7719Mean AUROC

SpikeScore

0.4683240.5471370.625950.704763Jan 27, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
0.7719
2026.01
0.7664
2026.01
0.7498
2026.01
0.7488
2026.01
0.7416
2026.01
0.7271
2026.01
0.7097
2026.01
0.7088
2026.01
0.7067
2026.01
0.7055
2026.01
0.7038
2026.01
0.6993
2026.01
0.6974
2026.01
0.696
2026.01
0.6887
2026.01
0.6882
2026.01
0.6777
2026.01
0.6769
2026.01
0.6727
2026.01
0.6684
2026.01
0.6632
2026.01
0.6611
2026.01
0.6515
2026.01
0.6449
2026.01
0.6445
2026.01
0.6423
2026.01
0.6368
2026.01
0.632
2026.01
0.6311
2026.01
0.6305
2026.01
0.6153
2026.01
0.5995
2026.01
0.556
2026.01
0.5358
2026.01
0.5345
2026.01
0.5228
2026.01
0.5119
2026.01
0.5077
2026.01
0.5074
2026.01
0.5004
2026.01
0.4985
2026.01
0.4952
2026.01
0.4933
2026.01
0.4923
2026.01
0.4893
2026.01
0.4866
2026.01
0.4854
2026.01
0.48