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

Hallucination Detection on SVAMP

80.6Mean AUROC

KLE

48.058456.506764.95573.4033Jan 27, 2026Feb 16, 2026Mar 8, 2026Mar 28, 2026Apr 17, 2026May 7, 2026May 27, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
80.6
2026.05
78.4
2026.01
78.37
2026.01
77.51
2026.01
73.44
2026.01
72.52
2026.01
71.7
2026.01
70.78
2026.01
70.58
2026.01
70.5
2026.01
70.14
2026.01
70.1
2026.01
69.79
2026.01
69.78
2026.01
69.04
2026.01
68.11
2026.01
68.09
2026.01
67.84
2026.01
67.18
2026.01
66.82
2026.01
66.81
2026.01
66.66
2026.01
66.36
2026.01
65.69
2026.01
65.44
2026.01
65.05
2026.01
65.03
2026.01
64.93
2026.01
63.79
2026.01
63.62
2026.01
63.1
2026.01
62.24
2026.01
61.49
2026.01
60.13
2026.01
58.55
2026.01
58.08
2026.01
57.95
2026.01
57.9
2026.01
57.88
2026.01
57.78
2026.01
57.6
2026.01
57.53
2026.01
55.29
2026.01
54.3
2026.01
54.2
2026.01
53.26
2026.01
52.37
2026.01
51.23
2026.01
51.19
2026.01
49.31