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

Hallucination Detection on Math

81.57Mean AUROC

SpikeScore

48.373256.991665.6174.2284Jan 27, 2026Jan 29, 2026Jan 31, 2026Feb 2, 2026Feb 4, 2026Feb 6, 2026Feb 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
81.57
2026.01
80.04
2026.01
76.99
2026.01
76.15
2026.01
75.04
2026.01
74.87
2026.01
74.34
2026.01
72.81
2026.02
72
2026.02
72
2026.02
72
2026.02
72
2026.02
71
2026.01
70.43
2026.01
70.41
2026.02
70
2026.01
69.95
2026.01
69.46
2026.01
68.52
2026.01
68.12
2026.02
68
2026.02
68
2026.02
68
2026.01
67.85
2026.01
67.71
2026.01
67.53
2026.02
67
2026.01
66.25
2026.01
65.31
2026.01
65.16
2026.01
65.15
2026.01
64.81
2026.01
64.75
2026.01
64.48
2026.01
64.27
2026.01
64.22
2026.01
63.43
2026.01
63.33
2026.01
63.07
2026.01
61.26
2026.02
61
2026.01
60.63
2026.01
60.51
2026.01
60.03
2026.01
59.76
2026.01
59.58
2026.02
59
2026.02
59
2026.02
59
2026.02
59
2026.01
58.61
2026.01
58.41
2026.01
57.89
2026.01
57.67
2026.02
57
2026.02
57
2026.01
56.85
2026.02
56
2026.01
55.5
2026.02
55
2026.01
54.36
2026.01
54.2
2026.02
54
2026.01
53.9
2026.01
53.09
2026.01
53.08
2026.02
52
2026.02
52
2026.02
51
2026.02
51
2026.01
50.9
2026.01
49.65