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

Hallucination Detection on NQ-Open

0.9304AUROC

HCPD

0.6219360.7020180.78210.862182Jan 4, 2026Jan 31, 2026Feb 27, 2026Mar 27, 2026Apr 23, 2026May 20, 2026Jun 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.9304
2026.06
0.9294
2026.06
0.9245
2026.06
0.916
2026.06
0.9042
2026.06
0.9038
2026.06
0.9038
2026.01
0.8843
2026.06
0.8735
2026.06
0.8735
2026.01
0.8604
2026.06
0.8588
2026.01
0.8584
2026.01
0.8584
2026.06
0.857
2026.01
0.8376
2026.01
0.8328
2026.01
0.8296
2026.04
0.821
2026.04
0.82
2026.04
0.818
2026.04
0.816
2026.06
0.8051
2026.01
0.8022
2026.04
0.801
2026.01
0.7987
2026.01
0.7962
2026.06
0.7942
2026.04
0.789
2026.04
0.787
2026.04
0.787
2026.06
0.7862
2026.03
0.7861
2026.04
0.782
2026.04
0.779
2026.04
0.776
2026.04
0.776
2026.01
0.7757
2026.06
0.775
2026.04
0.772
2026.06
0.7682
2026.04
0.765
2026.06
0.7623
2026.06
0.7623
2026.04
0.759
2026.04
0.759
2026.04
0.758
2026.01
0.7548
2026.04
0.754
2026.06
0.751
2026.04
0.75
2026.06
0.75
2026.01
0.748
2026.06
0.7435
2026.04
0.743
2026.04
0.736
2026.05
0.733
2026.01
0.732
2026.04
0.732
2026.01
0.73
2026.04
0.73
2026.04
0.729
2026.06
0.7286
2026.06
0.7286
2026.04
0.723
2026.01
0.715
2026.01
0.712
2026.03
0.7114
2026.06
0.7055
2026.01
0.7033
2026.06
0.7017
2026.06
0.7017
2026.06
0.7
2026.01
0.694
2026.01
0.693
2026.06
0.6888
2026.06
0.6887
2026.01
0.688
2026.06
0.688
2026.06
0.687
2026.06
0.6852
2026.01
0.685
2026.06
0.6827
2026.01
0.682
2026.03
0.6804
2026.03
0.6797
2026.06
0.6781
2026.04
0.677
2026.01
0.6705
2026.01
0.6697
2026.06
0.6685
2026.06
0.6677
2026.04
0.666
2026.04
0.661
2026.03
0.6585
2026.06
0.6555
2026.06
0.6484
2026.06
0.6382
2026.06
0.6368
2026.06
0.6338
Showing 100 of 141 rows